Abstract
Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively exploit the spatial-temporal information is a critical question for 3D LiDAR moving object segmentation (LiDAR-MOS). In this work, we propose a novel deep neural network exploiting both spatial-temporal information and different representation modalities of LiDAR scans to improve LiDAR-MOS performance. Specifically, we first use a range image-based dual-branch structure to separately deal with spatial and temporal information that can be obtained from sequential LiDAR scans, and later combine them using motion-guided attention modules. We also use a point refinement module via 3D sparse convolution to fuse the information from both LiDAR range image and point cloud representations and reduce the artifacts on the borders of the objects. We verify the effectiveness of our proposed approach on the LiDAR-MOS benchmark of SemanticKITTI. Our method outperforms the state-of-the-art methods significantly in terms of LiDAR-MOS IoU. Benefiting from the devised coarse-to-fine architecture, our method operates online at sensor frame rate. The implementation of our method is available as open source at: https://github.com/haomo-ai/MotionSeg3D.
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Abstract
Bird's eye view (BEV) semantic segmentation plays a crucial role in spatial sensing for autonomous driving. Although recent literature has made significant progress on BEV map understanding, they are all based on single-agent camera-based systems which are difficult to handle occlusions and detect distant objects in complex traffic scenes. Vehicle-to-Vehicle (V2V) communication technologies have enabled autonomous vehicles to share sensing information, which can dramatically improve the perception performance and range as compared to single-agent systems. In this paper, we propose CoBEVT, the first generic multi-agent multi-camera perception framework that can cooperatively generate BEV map predictions. To efficiently fuse camera features from multi-view and multi-agent data in an underlying Transformer architecture, we design a fused axial attention or FAX module, which can capture sparsely local and global spatial interactions across views and agents. The extensive experiments on the V2V perception dataset, OPV2V, demonstrate that CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation. Moreover, CoBEVT is shown to be generalizable to other tasks, including 1) BEV segmentation with single-agent multi-camera and 2) 3D object detection with multi-agent LiDAR systems, and achieves state-of-the-art performance with real-time inference speed.
Keyword: loop detection
There is no result
Keyword: nerf
There is no result
Keyword: mapping
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Authors: Chuan Guo, Xinxin Xuo, Sen Wang, Li Cheng
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Inspired by the strong ties between vision and language, the two intimate human sensing and communication modalities, our paper aims to explore the generation of 3D human full-body motions from texts, as well as its reciprocal task, shorthanded for text2motion and motion2text, respectively. To tackle the existing challenges, especially to enable the generation of multiple distinct motions from the same text, and to avoid the undesirable production of trivial motionless pose sequences, we propose the use of motion token, a discrete and compact motion representation. This provides one level playing ground when considering both motions and text signals, as the motion and text tokens, respectively. Moreover, our motion2text module is integrated into the inverse alignment process of our text2motion training pipeline, where a significant deviation of synthesized text from the input text would be penalized by a large training loss; empirically this is shown to effectively improve performance. Finally, the mappings in-between the two modalities of motions and texts are facilitated by adapting the neural model for machine translation (NMT) to our context. This autoregressive modeling of the distribution over discrete motion tokens further enables non-deterministic production of pose sequences, of variable lengths, from an input text. Our approach is flexible, could be used for both text2motion and motion2text tasks. Empirical evaluations on two benchmark datasets demonstrate the superior performance of our approach on both tasks over a variety of state-of-the-art methods. Project page: https://ericguo5513.github.io/TM2T/
Making sense of spoken plurals
Authors: Elnaz Shafaei-Bajestan, Peter Uhrig, R. Harald Baayen
Abstract
Distributional semantics offers new ways to study the semantics of morphology. This study focuses on the semantics of noun singulars and their plural inflectional variants in English. Our goal is to compare two models for the conceptualization of plurality. One model (FRACSS) proposes that all singular-plural pairs should be taken into account when predicting plural semantics from singular semantics. The other model (CCA) argues that conceptualization for plurality depends primarily on the semantic class of the base word. We compare the two models on the basis of how well the speech signal of plural tokens in a large corpus of spoken American English aligns with the semantic vectors predicted by the two models. Two measures are employed: the performance of a form-to-meaning mapping and the correlations between form distances and meaning distances. Results converge on a superior alignment for CCA. Our results suggest that usage-based approaches to pluralization in which a given word's own semantic neighborhood is given priority outperform theories according to which pluralization is conceptualized as a process building on high-level abstraction. We see that what has often been conceived of as a highly abstract concept, [+plural], is better captured via a family of mid-level partial generalizations.
Abstract
In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for four Ego4D challenge tasks, including Natural Language Query (NLQ), Moment Query (MQ), Object State Change Classification (OSCC), and PNR Localization (PNR). Especially, we exploit the recently released Ego4D dataset \cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation or video-only representation to several video downstream tasks. Our Egocentric VLP achieves 10.46R@1&IoU @0.3 on NLQ, 10.33 mAP on MQ, 74% Acc on OSCC, 0.67 sec error on PNR. The code is available at https://github.com/showlab/EgoVLP.
Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning
Abstract
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability. Moreover, it is extremely laborious and expensive to collect and fully annotate a point-cloud detection dataset with numerous classes of objects, leading to the limited classes of existing point-cloud datasets and hindering the model to learn general representations to achieve open-vocabulary point-cloud detection. As far as we know, we are the first to study the problem of open-vocabulary 3D point-cloud detection. Instead of seeking a point-cloud dataset with full labels, we resort to ImageNet1K to broaden the vocabulary of the point-cloud detector. We propose OV-3DETIC, an Open-Vocabulary 3D DETector using Image-level Class supervision. Specifically, we take advantage of two modalities, the image modality for recognition and the point-cloud modality for localization, to generate pseudo labels for unseen classes. Then we propose a novel debiased cross-modal contrastive learning method to transfer the knowledge from image modality to point-cloud modality during training. Without hurting the latency during inference, OV-3DETIC makes the point-cloud detector capable of achieving open-vocabulary detection. Extensive experiments demonstrate that the proposed OV-3DETIC achieves at least 10.77 % mAP improvement (absolute value) and 9.56 % mAP improvement (absolute value) by a wide range of baselines on the SUN-RGBD dataset and ScanNet dataset, respectively. Besides, we conduct sufficient experiments to shed light on why the proposed OV-3DETIC works.
MVP: Robust Multi-View Practice for Driving Action Localization
Authors: Jingjie Shang, Kunchang Li, Kaibin Tian, Haisheng Su, Yangguang Li
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Distracted driving causes thousands of deaths per year, and how to apply deep-learning methods to prevent these tragedies has become a crucial problem. In Track3 of the 6th AI City Challenge, researchers provide a high-quality video dataset with densely action annotations. Due to the small data scale and unclear action boundary, the dataset presents a unique challenge to precisely localize all the different actions and classify their categories. In this paper, we make good use of the multi-view synchronization among videos, and conduct robust Multi-View Practice (MVP) for driving action localization. To avoid overfitting, we fine-tune SlowFast with Kinetics-700 pre-training as the feature extractor. Then the features of different views are passed to ActionFormer to generate candidate action proposals. For precisely localizing all the actions, we design elaborate post-processing, including model voting, threshold filtering and duplication removal. The results show that our MVP is robust for driving action localization, which achieves 28.49% F1-score in the Track3 test set.
Data Integrity Error Localization in Networked Systems with Missing Data
Abstract
Most recent network failure diagnosis systems focused on data center networks where complex measurement systems can be deployed to derive routing information and ensure network coverage in order to achieve accurate and fast fault localization. In this paper, we target wide-area networks that support data-intensive distributed applications. We first present a new multi-output prediction model that directly maps the application level observations to localize the system component failures. In reality, this application-centric approach may face the missing data challenge as some input (feature) data to the inference models may be missing due to incomplete or lost measurements in wide area networks. We show that the presented prediction model naturally allows the {\it multivariate} imputation to recover the missing data. We evaluate multiple imputation algorithms and show that the prediction performance can be improved significantly in a large-scale network. As far as we know, this is the first study on the missing data issue and applying imputation techniques in network failure localization.
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
Authors: Gary Leung, Jun Gao, Xiaohui Zeng, Sanja Fidler
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Existing transformer-based image backbones typically propagate feature information in one direction from lower to higher-levels. This may not be ideal since the localization ability to delineate accurate object boundaries, is most prominent in the lower, high-resolution feature maps, while the semantics that can disambiguate image signals belonging to one object vs. another, typically emerges in a higher level of processing. We present Hierarchical Inter-Level Attention (HILA), an attention-based method that captures Bottom-Up and Top-Down Updates between features of different levels. HILA extends hierarchical vision transformer architectures by adding local connections between features of higher and lower levels to the backbone encoder. In each iteration, we construct a hierarchy by having higher-level features compete for assignments to update lower-level features belonging to them, iteratively resolving object-part relationships. These improved lower-level features are then used to re-update the higher-level features. HILA can be integrated into the majority of hierarchical architectures without requiring any changes to the base model. We add HILA into SegFormer and the Swin Transformer and show notable improvements in accuracy in semantic segmentation with fewer parameters and FLOPS. Project website and code: https://www.cs.toronto.edu/~garyleung/hila/
Tackling Real-World Autonomous Driving using Deep Reinforcement Learning
Authors: Paolo Maramotti, Alessandro Paolo Capasso, Giulio Bacchiani, Alberto Broggi
Abstract
In the typical autonomous driving stack, planning and control systems represent two of the most crucial components in which data retrieved by sensors and processed by perception algorithms are used to implement a safe and comfortable self-driving behavior. In particular, the planning module predicts the path the autonomous car should follow taking the correct high-level maneuver, while control systems perform a sequence of low-level actions, controlling steering angle, throttle and brake. In this work, we propose a model-free Deep Reinforcement Learning Planner training a neural network that predicts both acceleration and steering angle, thus obtaining a single module able to drive the vehicle using the data processed by localization and perception algorithms on board of the self-driving car. In particular, the system that was fully trained in simulation is able to drive smoothly and safely in obstacle-free environments both in simulation and in a real-world urban area of the city of Parma, proving that the system features good generalization capabilities also driving in those parts outside the training scenarios. Moreover, in order to deploy the system on board of the real self-driving car and to reduce the gap between simulated and real-world performances, we also develop a module represented by a tiny neural network able to reproduce the real vehicle dynamic behavior during the training in simulation.
Keyword: transformer
GazBy: Gaze-Based BERT Model to Incorporate Human Attention in Neural Information Retrieval
Authors: Sibo Dong, Justin Goldstein, Grace Hui Yang
Abstract
This paper is interested in investigating whether human gaze signals can be leveraged to improve state-of-the-art search engine performance and how to incorporate this new input signal marked by human attention into existing neural retrieval models. In this paper, we propose GazBy ({\bf Gaz}e-based {\bf B}ert model for document relevanc{\bf y}), a light-weight joint model that integrates human gaze fixation estimation into transformer models to predict document relevance, incorporating more nuanced information about cognitive processing into information retrieval (IR). We evaluate our model on the Text Retrieval Conference (TREC) Deep Learning (DL) 2019 and 2020 Tracks. Our experiments show encouraging results and illustrate the effective and ineffective entry points for using human gaze to help with transformer-based neural retrievers. With the rise of virtual reality (VR) and augmented reality (AR), human gaze data will become more available. We hope this work serves as a first step exploring using gaze signals in modern neural search engines.
Interaction Transformer for Human Reaction Generation
Authors: Baptiste Chopin, Hao Tang, Naima Otberdout, Mohamed Daoudi, Nicu Sebe
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
We address the challenging task of human reaction generation which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate the motion when only the action is given as input. To address this limitation, we propose a novel interaction Transformer (InterFormer) consisting of a Transformer network with both temporal and spatial attentions. Specifically, the temporal attention captures the temporal dependencies of the motion of both characters and of their interaction, while the spatial attention learns the dependencies between the different body parts of each character and those which are part of the interaction. Moreover, we propose using graphs to increase the performance of the spatial attention via an interaction distance module that helps focus on nearby joints from both characters. Extensive experiments on the SBU interaction, K3HI, and DuetDance datasets demonstrate the effectiveness of InterFormer. Our method is general and can be used to generate more complex and long-term interactions.
An adaptive music generation architecture for games based on the deep learning Transformer mode
Authors: Gustavo Amaral Costa dos Santos, Augusto Baffa, Jean-Pierre Briot, Bruno Feijó, Antonio Luz Furtado
Abstract
This paper presents an architecture for generating music for video games based on the Transformer deep learning model. The system generates music in various layers, following the standard layering strategy currently used by composers designing video game music. The music is adaptive to the psychological context of the player, according to the arousal-valence model. Our motivation is to customize music according to the player's tastes, who can select his preferred style of music through a set of training examples of music. We discuss current limitations and prospects for the future, such as collaborative and interactive control of the musical components.
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
Authors: Brooke Stephenson, Laurent Besacier, Laurent Girin, Thomas Hueber
Subjects: Computation and Language (cs.CL); Audio and Speech Processing (eess.AS)
Abstract
Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have explored prosody in general, in this work, we look specifically at the prediction of contrastive focus on personal pronouns. This is a particularly challenging task as it often requires semantic, discursive and/or pragmatic knowledge to predict correctly. We collect a corpus of utterances containing contrastive focus and we evaluate the accuracy of a BERT model, finetuned to predict quantized acoustic prominence features, on these samples. We also investigate how past utterances can provide relevant information for this prediction. Furthermore, we evaluate the controllability of pronoun prominence in a TTS model conditioned on acoustic prominence features.
3D Part Assembly Generation with Instance Encoded Transformer
Authors: Rufeng Zhang, Tao Kong, Weihao Wang, Xuan Han, Mingyu You
Subjects: Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
Abstract
It is desirable to enable robots capable of automatic assembly. Structural understanding of object parts plays a crucial role in this task yet remains relatively unexplored. In this paper, we focus on the setting of furniture assembly from a complete set of part geometries, which is essentially a 6-DoF part pose estimation problem. We propose a multi-layer transformer-based framework that involves geometric and relational reasoning between parts to update the part poses iteratively. We carefully design a unique instance encoding to solve the ambiguity between geometrically-similar parts so that all parts can be distinguished. In addition to assembling from scratch, we extend our framework to a new task called in-process part assembly. Analogous to furniture maintenance, it requires robots to continue with unfinished products and assemble the remaining parts into appropriate positions. Our method achieves far more than 10% improvements over the current state-of-the-art in multiple metrics on the public PartNet dataset. Extensive experiments and quantitative comparisons demonstrate the effectiveness of the proposed framework.
Multimodal Frame-Scoring Transformer for Video Summarization
Authors: Jeiyoon Park, Kiho Kwoun, Chanhee Lee, Heuiseok Lim
Abstract
As the number of video content has mushroomed in recent years, automatic video summarization has come useful when we want to just peek at the content of the video. However, there are two underlying limitations in generic video summarization task. First, most previous approaches read in just visual features as input, leaving other modality features behind. Second, existing datasets for generic video summarization are relatively insufficient to train a caption generator and multimodal feature extractors. To address these two problems, this paper proposes the Multimodal Frame-Scoring Transformer (MFST) framework exploiting visual, text and audio features and scoring a video with respect to frames. Our MFST framework first extracts each modality features (visual-text-audio) using pretrained encoders. Then, MFST trains the multimodal frame-scoring transformer that uses video-text-audio representations as inputs and predicts frame-level scores. Our extensive experiments with previous models and ablation studies on TVSum and SumMe datasets demonstrate the effectiveness and superiority of our proposed method.
Efficient Representation Learning via Adaptive Context Pooling
Authors: Chen Huang, Walter Talbott, Navdeep Jaitly, Josh Susskind
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)
Abstract
Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which may not be optimal for modeling complex dependencies at higher levels. In this paper, we propose ContextPool to address this problem by adapting the attention granularity for each token. Inspired by the success of ConvNets that are combined with pooling to capture long-range dependencies, we learn to pool neighboring features for each token before computing attention in a given attention layer. The pooling weights and support size are adaptively determined, allowing the pooled features to encode meaningful context with varying scale. We show that ContextPool makes attention models more expressive, achieving strong performance often with fewer layers and thus significantly reduced cost. Experiments validate that our ContextPool module, when plugged into transformer models, matches or surpasses state-of-the-art performance using less compute on several language and image benchmarks, outperforms recent works with learned context sizes or sparse attention patterns, and is also applicable to ConvNets for efficient feature learning.
Meta-Learning a Real-Time Tabular AutoML Method For Small Data
Authors: Noah Hollmann, Samuel Müller, Katharina Eggensperger, Frank Hutter
Abstract
We present TabPFN, an AutoML method that is competitive with the state of the art on small tabular datasets while being over 1,000$\times$ faster. Our method is very simple: it is fully entailed in the weights of a single neural network, and a single forward pass directly yields predictions for a new dataset. Our AutoML method is meta-learned using the Transformer-based Prior-Data Fitted Network (PFN) architecture and approximates Bayesian inference with a prior that is based on assumptions of simplicity and causal structures. The prior contains a large space of structural causal models and Bayesian neural networks with a bias for small architectures and thus low complexity. Furthermore, we extend the PFN approach to differentiably calibrate the prior's hyperparameters on real data. By doing so, we separate our abstract prior assumptions from their heuristic calibration on real data. Afterwards, the calibrated hyperparameters are fixed and TabPFN can be applied to any new tabular dataset at the push of a button. Finally, on 30 datasets from the OpenML-CC18 suite we show that our method outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with predictions produced in less than a second. We provide all our code and our final trained TabPFN in the supplementary materials.
WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training
Authors: Zewang Zhang, Yibin Zheng, Xinhui Li, Li Lu
Subjects: Sound (cs.SD); Audio and Speech Processing (eess.AS)
Abstract
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce high-quality singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random area conditional discriminators to help supervise the acoustic model, which can effectively avoid the over-smoothed spectrogram prediction by the duration-allocated Transformer-based acoustic model. On the other hand, we subtly combined the spectrogram with the frame-level linearly-interpolated F0 sequence as the input for the neural vocoder, which is then optimized with the help of multiple adversarial discriminators in the waveform domain and multi-scale distance functions in the frequency domain. The experimental results and ablation studies concluded that, compared with our previous auto-regressive work, our new system can produce high-quality singing voices efficiently by fine-tuning on different singing datasets covering several minutes to a few hours. Some synthesized singing samples are available online [https://zzw922cn.github.io/wesinger2 ].
FishFormer: Annulus Slicing-based Transformer for Fisheye Rectification with Efficacy Domain Exploration
Authors: Shangrong Yang, Chunyu Lin, Kang Liao, Yao Zhao
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Numerous significant progress on fisheye image rectification has been achieved through CNN. Nevertheless, constrained by a fixed receptive field, the global distribution and the local symmetry of the distortion have not been fully exploited. To leverage these two characteristics, we introduced Fishformer that processes the fisheye image as a sequence to enhance global and local perception. We tuned the Transformer according to the structural properties of fisheye images. First, the uneven distortion distribution in patches generated by the existing square slicing method confuses the network, resulting in difficult training. Therefore, we propose an annulus slicing method to maintain the consistency of the distortion in each patch, thus perceiving the distortion distribution well. Second, we analyze that different distortion parameters have their own efficacy domains. Hence, the perception of the local area is as important as the global, but Transformer has a weakness for local texture perception. Therefore, we propose a novel layer attention mechanism to enhance the local perception and texture transfer. Our network simultaneously implements global perception and focused local perception decided by the different parameters. Extensive experiments demonstrate that our method provides superior performance compared with state-of-the-art methods.
Block-SCL: Blocking Matters for Supervised Contrastive Learning in Product Matching
Authors: Mario Almagro, David Jiménez, Diego Ortego, Emilio Almazán, Eva Martínez
Abstract
Product matching is a fundamental step for the global understanding of consumer behavior in e-commerce. In practice, product matching refers to the task of deciding if two product offers from different data sources (e.g. retailers) represent the same product. Standard pipelines use a previous stage called blocking, where for a given product offer a set of potential matching candidates are retrieved based on similar characteristics (e.g. same brand, category, flavor, etc.). From these similar product candidates, those that are not a match can be considered hard negatives. We present Block-SCL, a strategy that uses the blocking output to make the most of Supervised Contrastive Learning (SCL). Concretely, Block-SCL builds enriched batches using the hard-negatives samples obtained in the blocking stage. These batches provide a strong training signal leading the model to learn more meaningful sentence embeddings for product matching. Experimental results in several public datasets demonstrate that Block-SCL achieves state-of-the-art results despite only using short product titles as input, no data augmentation, and a lighter transformer backbone than competing methods.
CASHformer: Cognition Aware SHape Transformer for Longitudinal Analysis
Authors: Ignacio Sarasua, Sebastian Pölsterl, Christian Wachinger
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Modeling temporal changes in subcortical structures is crucial for a better understanding of the progression of Alzheimer's disease (AD). Given their flexibility to adapt to heterogeneous sequence lengths, mesh-based transformer architectures have been proposed in the past for predicting hippocampus deformations across time. However, one of the main limitations of transformers is the large amount of trainable parameters, which makes the application on small datasets very challenging. In addition, current methods do not include relevant non-image information that can help to identify AD-related patterns in the progression. To this end, we introduce CASHformer, a transformer-based framework to model longitudinal shape trajectories in AD. CASHformer incorporates the idea of pre-trained transformers as universal compute engines that generalize across a wide range of tasks by freezing most layers during fine-tuning. This reduces the number of parameters by over 90% with respect to the original model and therefore enables the application of large models on small datasets without overfitting. In addition, CASHformer models cognitive decline to reveal AD atrophy patterns in the temporal sequence. Our results show that CASHformer reduces the reconstruction error by 73% compared to previously proposed methods. Moreover, the accuracy of detecting patients progressing to AD increases by 3% with imputing missing longitudinal shape data.
Neural Networks and the Chomsky Hierarchy
Authors: Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Marcus Hutter, Shane Legg, Pedro A. Ortega
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Formal Languages and Automata Theory (cs.FL)
Abstract
Reliable generalization lies at the heart of safe ML and AI. However, understanding when and how neural networks generalize remains one of the most important unsolved problems in the field. In this work, we conduct an extensive empirical study (2200 models, 16 tasks) to investigate whether insights from the theory of computation can predict the limits of neural network generalization in practice. We demonstrate that grouping tasks according to the Chomsky hierarchy allows us to forecast whether certain architectures will be able to generalize to out-of-distribution inputs. This includes negative results where even extensive amounts of data and training time never led to any non-trivial generalization, despite models having sufficient capacity to perfectly fit the training data. Our results show that, for our subset of tasks, RNNs and Transformers fail to generalize on non-regular tasks, LSTMs can solve regular and counter-language tasks, and only networks augmented with structured memory (such as a stack or memory tape) can successfully generalize on context-free and context-sensitive tasks.
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
Authors: Gary Leung, Jun Gao, Xiaohui Zeng, Sanja Fidler
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Existing transformer-based image backbones typically propagate feature information in one direction from lower to higher-levels. This may not be ideal since the localization ability to delineate accurate object boundaries, is most prominent in the lower, high-resolution feature maps, while the semantics that can disambiguate image signals belonging to one object vs. another, typically emerges in a higher level of processing. We present Hierarchical Inter-Level Attention (HILA), an attention-based method that captures Bottom-Up and Top-Down Updates between features of different levels. HILA extends hierarchical vision transformer architectures by adding local connections between features of higher and lower levels to the backbone encoder. In each iteration, we construct a hierarchy by having higher-level features compete for assignments to update lower-level features belonging to them, iteratively resolving object-part relationships. These improved lower-level features are then used to re-update the higher-level features. HILA can be integrated into the majority of hierarchical architectures without requiring any changes to the base model. We add HILA into SegFormer and the Swin Transformer and show notable improvements in accuracy in semantic segmentation with fewer parameters and FLOPS. Project website and code: https://www.cs.toronto.edu/~garyleung/hila/
Multi-modal Robustness Analysis Against Language and Visual Perturbations
Authors: Madeline C. Schiappa, Yogesh S. Rawat, Shruti Vyas, Vibhav Vineet, Hamid Palangi
Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
Abstract
Joint visual and language modeling on large-scale datasets has recently shown a good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been studied. In this work, we perform the first extensive robustness study of such models against various real-world perturbations focusing on video and language. We focus on text-to-video retrieval and propose two large-scale benchmark datasets, MSRVTT-P and YouCook2-P, which utilize 90 different visual and 35 different textual perturbations. The study reveals some interesting findings: 1) The studied models are more robust when text is perturbed versus when video is perturbed 2) The transformer text encoder is more robust on non-semantic changing text perturbations and visual perturbations compared to word embedding approaches. 3) Using two-branch encoders in isolation is typically more robust than when architectures use cross-attention. We hope this study will serve as a benchmark and guide future research in robust multimodal learning.
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Abstract
Bird's eye view (BEV) semantic segmentation plays a crucial role in spatial sensing for autonomous driving. Although recent literature has made significant progress on BEV map understanding, they are all based on single-agent camera-based systems which are difficult to handle occlusions and detect distant objects in complex traffic scenes. Vehicle-to-Vehicle (V2V) communication technologies have enabled autonomous vehicles to share sensing information, which can dramatically improve the perception performance and range as compared to single-agent systems. In this paper, we propose CoBEVT, the first generic multi-agent multi-camera perception framework that can cooperatively generate BEV map predictions. To efficiently fuse camera features from multi-view and multi-agent data in an underlying Transformer architecture, we design a fused axial attention or FAX module, which can capture sparsely local and global spatial interactions across views and agents. The extensive experiments on the V2V perception dataset, OPV2V, demonstrate that CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation. Moreover, CoBEVT is shown to be generalizable to other tasks, including 1) BEV segmentation with single-agent multi-camera and 2) 3D object detection with multi-agent LiDAR systems, and achieves state-of-the-art performance with real-time inference speed.
Detecting and Recovering Sequential DeepFake Manipulation
Authors: Rui Shao, Tianxing Wu, Ziwei Liu
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Since photorealistic faces can be readily generated by facial manipulation technologies nowadays, potential malicious abuse of these technologies has drawn great concerns. Numerous deepfake detection methods are thus proposed. However, existing methods only focus on detecting one-step facial manipulation. As the emergence of easy-accessible facial editing applications, people can easily manipulate facial components using multi-step operations in a sequential manner. This new threat requires us to detect a sequence of facial manipulations, which is vital for both detecting deepfake media and recovering original faces afterwards. Motivated by this observation, we emphasize the need and propose a novel research problem called Detecting Sequential DeepFake Manipulation (Seq-DeepFake). Unlike the existing deepfake detection task only demanding a binary label prediction, detecting Seq-DeepFake manipulation requires correctly predicting a sequential vector of facial manipulation operations. To support a large-scale investigation, we construct the first Seq-DeepFake dataset, where face images are manipulated sequentially with corresponding annotations of sequential facial manipulation vectors. Based on this new dataset, we cast detecting Seq-DeepFake manipulation as a specific image-to-sequence (e.g. image captioning) task and propose a concise yet effective Seq-DeepFake Transformer (SeqFakeFormer). Moreover, we build a comprehensive benchmark and set up rigorous evaluation protocols and metrics for this new research problem. Extensive experiments demonstrate the effectiveness of SeqFakeFormer. Several valuable observations are also revealed to facilitate future research in broader deepfake detection problems.
Segmenting Moving Objects via an Object-Centric Layered Representation
Authors: Junyu Xie, Weidi Xie, Andrew Zisserman
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer representation. This is implemented using a variant of the transformer architecture that ingests optical flow, where each query vector specifies an object and its layer for the entire video. The model can effectively discover multiple moving objects and handle mutual occlusions; Second, we introduce a scalable pipeline for generating synthetic training data with multiple objects, significantly reducing the requirements for labour-intensive annotations, and supporting Sim2Real generalisation; Third, we show that the model is able to learn object permanence and temporal shape consistency, and is able to predict amodal segmentation masks; Fourth, we evaluate the model on standard video segmentation benchmarks, DAVIS, MoCA, SegTrack, FBMS-59, and achieve state-of-the-art unsupervised segmentation performance, even outperforming several supervised approaches. With test-time adaptation, we observe further performance boosts.
Keyword: autonomous driving
How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Authors: Rafid Mahmood, James Lucas, David Acuna, Daiqing Li, Jonah Philion, Jose M. Alvarez, Zhiding Yu, Sanja Fidler, Marc T. Law
Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Abstract
Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance? This question is of critical importance in applications such as autonomous driving or medical imaging where collecting data is expensive and time-consuming. Overestimating or underestimating data requirements incurs substantial costs that could be avoided with an adequate budget. Prior work on neural scaling laws suggest that the power-law function can fit the validation performance curve and extrapolate it to larger data set sizes. We find that this does not immediately translate to the more difficult downstream task of estimating the required data set size to meet a target performance. In this work, we consider a broad class of computer vision tasks and systematically investigate a family of functions that generalize the power-law function to allow for better estimation of data requirements. Finally, we show that incorporating a tuned correction factor and collecting over multiple rounds significantly improves the performance of the data estimators. Using our guidelines, practitioners can accurately estimate data requirements of machine learning systems to gain savings in both development time and data acquisition costs.
GP22: A Car Styling Dataset for Automotive Designers
Authors: Gyunpyo Lee, Taesu Kim, Hyeon-Jeong Suk
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Abstract
An automated design data archiving could reduce the time wasted by designers from working creatively and effectively. Though many datasets on classifying, detecting, and instance segmenting on car exterior exist, these large datasets are not relevant for design practices as the primary purpose lies in autonomous driving or vehicle verification. Therefore, we release GP22, composed of car styling features defined by automotive designers. The dataset contains 1480 car side profile images from 37 brands and ten car segments. It also contains annotations of design features that follow the taxonomy of the car exterior design features defined in the eye of the automotive designer. We trained the baseline model using YOLO v5 as the design feature detection model with the dataset. The presented model resulted in an mAP score of 0.995 and a recall of 0.984. Furthermore, exploration of the model performance on sketches and rendering images of the car side profile implies the scalability of the dataset for design purposes.
Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games
Authors: Lei Zhang, Mukesh Ghimire, Wenlong Zhang, Zhe Xu, Yi Ren
Subjects: Machine Learning (cs.LG); Computer Science and Game Theory (cs.GT); Robotics (cs.RO)
Abstract
Finding Nash equilibrial policies for two-player differential games requires solving Hamilton-Jacobi-Isaacs PDEs. Recent studies achieved success in circumventing the curse of dimensionality in solving such PDEs with underlying applications to human-robot interactions (HRI), by adopting self-supervised (physics-informed) neural networks as universal value approximators. This paper extends from previous SOTA on zero-sum games with continuous values to general-sum games with discontinuous values, where the discontinuity is caused by that of the players' losses. We show that due to its lack of convergence proof and generalization analysis on discontinuous losses, the existing self-supervised learning technique fails to generalize and raises safety concerns in an autonomous driving application. Our solution is to first pre-train the value network on supervised Nash equilibria, and then refine it by minimizing a loss that combines the supervised data with the PDE and boundary conditions. Importantly, the demonstrated advantage of the proposed learning method against purely supervised and self-supervised approaches requires careful choice of the neural activation function: Among $\texttt{relu}$, $\texttt{sin}$, and $\texttt{tanh}$, we show that $\texttt{tanh}$ is the only choice that achieves optimal generalization and safety performance. Our conjecture is that $\texttt{tanh}$ (similar to $\texttt{sin}$) allows continuity of value and its gradient, which is sufficient for the convergence of learning, and at the same time is expressive enough (similar to $\texttt{relu}$) at approximating discontinuous value landscapes. Lastly, we apply our method to approximating control policies for an incomplete-information interaction and demonstrate its contribution to safe interactions.
Object-Level Targeted Selection via Deep Template Matching
Authors: Suraj Kothawade, Donna Roy, Michele Fenzi, Elmar Haussmann, Jose M. Alvarez, Christoph Angerer
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned model or mitigating class imbalance in a dataset. The targeted selection task requires finding the relevant data from a large-scale pool of unlabeled data. Manual mining at this scale is infeasible. Further, the OOI are often small and occupy less than 1% of image area, are occluded, and co-exist with many semantically different objects in cluttered scenes. Existing semantic image retrieval methods often focus on mining for larger sized geographical landmarks, and/or require extra labeled data, such as images/image-pairs with similar objects, for mining images with generic objects. We propose a fast and robust template matching algorithm in the DNN feature space, that retrieves semantically similar images at the object-level from a large unlabeled pool of data. We project the region(s) around the OOI in the query image to the DNN feature space for use as the template. This enables our method to focus on the semantics of the OOI without requiring extra labeled data. In the context of autonomous driving, we evaluate our system for targeted selection by using failure cases of object detectors as OOI. We demonstrate its efficacy on a large unlabeled dataset with 2.2M images and show high recall in mining for images with small-sized OOI. We compare our method against a well-known semantic image retrieval method, which also does not require extra labeled data. Lastly, we show that our method is flexible and retrieves images with one or more semantically different co-occurring OOI seamlessly.
Tackling Real-World Autonomous Driving using Deep Reinforcement Learning
Authors: Paolo Maramotti, Alessandro Paolo Capasso, Giulio Bacchiani, Alberto Broggi
Abstract
In the typical autonomous driving stack, planning and control systems represent two of the most crucial components in which data retrieved by sensors and processed by perception algorithms are used to implement a safe and comfortable self-driving behavior. In particular, the planning module predicts the path the autonomous car should follow taking the correct high-level maneuver, while control systems perform a sequence of low-level actions, controlling steering angle, throttle and brake. In this work, we propose a model-free Deep Reinforcement Learning Planner training a neural network that predicts both acceleration and steering angle, thus obtaining a single module able to drive the vehicle using the data processed by localization and perception algorithms on board of the self-driving car. In particular, the system that was fully trained in simulation is able to drive smoothly and safely in obstacle-free environments both in simulation and in a real-world urban area of the city of Parma, proving that the system features good generalization capabilities also driving in those parts outside the training scenarios. Moreover, in order to deploy the system on board of the real self-driving car and to reduce the gap between simulated and real-world performances, we also develop a module represented by a tiny neural network able to reproduce the real vehicle dynamic behavior during the training in simulation.
Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation
Abstract
Accurate moving object segmentation is an essential task for autonomous driving. It can provide effective information for many downstream tasks, such as collision avoidance, path planning, and static map construction. How to effectively exploit the spatial-temporal information is a critical question for 3D LiDAR moving object segmentation (LiDAR-MOS). In this work, we propose a novel deep neural network exploiting both spatial-temporal information and different representation modalities of LiDAR scans to improve LiDAR-MOS performance. Specifically, we first use a range image-based dual-branch structure to separately deal with spatial and temporal information that can be obtained from sequential LiDAR scans, and later combine them using motion-guided attention modules. We also use a point refinement module via 3D sparse convolution to fuse the information from both LiDAR range image and point cloud representations and reduce the artifacts on the borders of the objects. We verify the effectiveness of our proposed approach on the LiDAR-MOS benchmark of SemanticKITTI. Our method outperforms the state-of-the-art methods significantly in terms of LiDAR-MOS IoU. Benefiting from the devised coarse-to-fine architecture, our method operates online at sensor frame rate. The implementation of our method is available as open source at: https://github.com/haomo-ai/MotionSeg3D.
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Abstract
Bird's eye view (BEV) semantic segmentation plays a crucial role in spatial sensing for autonomous driving. Although recent literature has made significant progress on BEV map understanding, they are all based on single-agent camera-based systems which are difficult to handle occlusions and detect distant objects in complex traffic scenes. Vehicle-to-Vehicle (V2V) communication technologies have enabled autonomous vehicles to share sensing information, which can dramatically improve the perception performance and range as compared to single-agent systems. In this paper, we propose CoBEVT, the first generic multi-agent multi-camera perception framework that can cooperatively generate BEV map predictions. To efficiently fuse camera features from multi-view and multi-agent data in an underlying Transformer architecture, we design a fused axial attention or FAX module, which can capture sparsely local and global spatial interactions across views and agents. The extensive experiments on the V2V perception dataset, OPV2V, demonstrate that CoBEVT achieves state-of-the-art performance for cooperative BEV semantic segmentation. Moreover, CoBEVT is shown to be generalizable to other tasks, including 1) BEV segmentation with single-agent multi-camera and 2) 3D object detection with multi-agent LiDAR systems, and achieves state-of-the-art performance with real-time inference speed.
New submissions for Wed, 6 Jul 22
Keyword: SLAM
There is no result
Keyword: odometry
There is no result
Keyword: livox
There is no result
Keyword: loam
There is no result
Keyword: lidar
Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Keyword: loop detection
There is no result
Keyword: nerf
There is no result
Keyword: mapping
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts
Making sense of spoken plurals
Keyword: localization
Egocentric Video-Language Pretraining @ Ego4D Challenge 2022
Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning
MVP: Robust Multi-View Practice for Driving Action Localization
Data Integrity Error Localization in Networked Systems with Missing Data
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
Tackling Real-World Autonomous Driving using Deep Reinforcement Learning
Keyword: transformer
GazBy: Gaze-Based BERT Model to Incorporate Human Attention in Neural Information Retrieval
Interaction Transformer for Human Reaction Generation
An adaptive music generation architecture for games based on the deep learning Transformer mode
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
3D Part Assembly Generation with Instance Encoded Transformer
Multimodal Frame-Scoring Transformer for Video Summarization
Efficient Representation Learning via Adaptive Context Pooling
Meta-Learning a Real-Time Tabular AutoML Method For Small Data
WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial Training
FishFormer: Annulus Slicing-based Transformer for Fisheye Rectification with Efficacy Domain Exploration
Block-SCL: Blocking Matters for Supervised Contrastive Learning in Product Matching
CASHformer: Cognition Aware SHape Transformer for Longitudinal Analysis
Neural Networks and the Chomsky Hierarchy
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
Multi-modal Robustness Analysis Against Language and Visual Perturbations
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
Detecting and Recovering Sequential DeepFake Manipulation
Segmenting Moving Objects via an Object-Centric Layered Representation
Keyword: autonomous driving
How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
GP22: A Car Styling Dataset for Automotive Designers
Approximating Discontinuous Nash Equilibrial Values of Two-Player General-Sum Differential Games
Object-Level Targeted Selection via Deep Template Matching
Tackling Real-World Autonomous Driving using Deep Reinforcement Learning
Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers