Abstract
Gaining spatial awareness of the Operating Room (OR) for surgical robotic systems is a key technology that can enable intelligent applications aiming at improved OR workflow. In this work, we present a method for semantic dense reconstruction of the OR scene using multiple RGB-D cameras attached and registered to the da Vinci Xi surgical system. We developed a novel SLAM approach for robot pose tracking in dynamic OR environments and dense reconstruction of the static OR table object. We validated our techniques in a mock OR by collecting data sequences with corresponding optical tracking trajectories as ground truth and manually annotated 100 frame segmentation masks. The mean absolute trajectory error is $11.4\pm1.9$ mm and the mean relative pose error is $1.53\pm0.48$ degrees per second. The segmentation DICE score is improved from 0.814 to 0.902 by using our SLAM system compared to single frame. Our approach effectively produces a dense OR table reconstruction in dynamic clinical environments as well as improved semantic segmentation on individual image frames.
HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
Authors: Zhixing Hou, Yan Yan, Chengzhong Xu, Hui Kong
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially divided into a sequence of small cells by downsampling and nearest neighbors searching. In the SRT, we extract the local feature for each point cell. While in the LRT, we build the global dependency among all of the point cells in the whole point cloud. Experiments on several standard benchmarks demonstrate the superiority of the HiTPR in terms of average recall rate, achieving 93.71% at top 1% and 86.63% at top 1 on the Oxford RobotCar dataset for example.
Keyword: Visual inertial
There is no result
Keyword: livox
There is no result
Keyword: loam
There is no result
Keyword: Visual inertial odometry
There is no result
Keyword: lidar
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Abstract
Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities. It has been widely agreed that vehicle-infrastructure cooperation is required to achieve Level 5 autonomy. However, there is still NO dataset from real scenarios available for computer vision researchers to work on vehicle-infrastructure cooperation-related problems. To accelerate computer vision research and innovation for Vehicle-Infrastructure Cooperative Autonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the first large-scale, multi-modality, multi-view dataset from real scenarios for VICAD. DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all frames are captured from real scenes with 3D annotations. The Vehicle-Infrastructure Cooperative 3D Object Detection problem (VIC3D) is introduced, formulating the problem of collaboratively locating and identifying 3D objects using sensory inputs from both vehicle and infrastructure. In addition to solving traditional 3D object detection problems, the solution of VIC3D needs to consider the temporal asynchrony problem between vehicle and infrastructure sensors and the data transmission cost between them. Furthermore, we propose Time Compensation Late Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmark based on DAIR-V2X. Find data, code, and more up-to-date information at https://thudair.baai.ac.cn/index and https://github.com/AIR-THU/DAIR-V2X.
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Abstract
In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robot or vehicle navigation in general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve very efficient 3D map representation of general environment thanks to the automatic local-OGM induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalability and compactness. In addition, we also evaluate localization accuracy extensively given the created LiDAR Road-Atlas representations on several public benchmark datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization errors of 0.26m (translation) and 1.07 degrees (rotation) on the Apollo dataset, and 0.89m (translation) and 1.29 degrees (rotation) on the MulRan dataset, respectively, at 10Hz, which validates the promising performance of our map representation for autonomous driving.
EVOPS Benchmark: Evaluation of Plane Segmentation from RGBD and LiDAR Data
Authors: Anastasiia Kornilova, Dmitrii Iarosh, Denis Kukushkin, Nikolai Goncharov, Pavel Mokeev, Arthur Saliou, Gonzalo Ferrer
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
Abstract
This paper provides the EVOPS dataset for plane segmentation from 3D data, both from RGBD images and LiDAR point clouds (PC). We have designed two annotation methodologies (RGBD and LiDAR) running on well-known and widely-used datasets and we have provided a complete set of benchmarking tools including point, planes and segmentation metrics. The data includes a total number of 10k RGBD and 7K LiDAR frames over different selected scenes which consist of high quality segmented planes. The experiments report quality of SOTA methods for RGBD plane segmentation on our annotated data. All labeled data and benchmark tools used have been made publicly available.
Keyword: loop detection
There is no result
Keyword: autonomous driving
Fully End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-Agent
Abstract
Focusing on the task of point-to-point navigation for an autonomous driving vehicle, we propose a novel deep learning model trained with end-to-end and multi-task learning manners to perform both perception and control tasks simultaneously. The model is used to drive the ego vehicle safely by following a sequence of routes defined by the global planner. The perception part of the model is used to encode high-dimensional observation data provided by an RGBD camera while performing semantic segmentation, semantic depth cloud (SDC) mapping, and traffic light state and stop sign prediction. Then, the control part decodes the encoded features along with additional information provided by GPS and speedometer to predict waypoints that come with a latent feature space. Furthermore, two agents are employed to process these outputs and make a control policy that determines the level of steering, throttle, and brake as the final action. The model is evaluated on CARLA simulator with various scenarios made of normal-adversarial situations and different weathers to mimic real-world conditions. In addition, we do a comparative study with some recent models to justify the performance in multiple aspects of driving. Moreover, we also conduct an ablation study on SDC mapping and multi-agent to understand their roles and behavior. As a result, our model achieves the highest driving score even with fewer parameters and computation load. To support future studies, we share our codes at https://github.com/oskarnatan/end-to-end-driving.
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
Abstract
Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities. It has been widely agreed that vehicle-infrastructure cooperation is required to achieve Level 5 autonomy. However, there is still NO dataset from real scenarios available for computer vision researchers to work on vehicle-infrastructure cooperation-related problems. To accelerate computer vision research and innovation for Vehicle-Infrastructure Cooperative Autonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the first large-scale, multi-modality, multi-view dataset from real scenarios for VICAD. DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all frames are captured from real scenes with 3D annotations. The Vehicle-Infrastructure Cooperative 3D Object Detection problem (VIC3D) is introduced, formulating the problem of collaboratively locating and identifying 3D objects using sensory inputs from both vehicle and infrastructure. In addition to solving traditional 3D object detection problems, the solution of VIC3D needs to consider the temporal asynchrony problem between vehicle and infrastructure sensors and the data transmission cost between them. Furthermore, we propose Time Compensation Late Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmark based on DAIR-V2X. Find data, code, and more up-to-date information at https://thudair.baai.ac.cn/index and https://github.com/AIR-THU/DAIR-V2X.
3DeformRS: Certifying Spatial Deformations on Point Clouds
Authors: Gabriel Pérez S., Juan C. Pérez, Motasem Alfarra, Silvio Giancola, Bernard Ghanem
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed practically and reliably. In this work, we propose 3DeformRS, a method to certify the robustness of point cloud Deep Neural Networks (DNNs) against real-world deformations. We developed 3DeformRS by building upon recent work that generalized Randomized Smoothing (RS) from pixel-intensity perturbations to vector-field deformations. In particular, we specialized RS to certify DNNs against parameterized deformations (e.g. rotation, twisting), while enjoying practical computational costs. We leverage the virtues of 3DeformRS to conduct a comprehensive empirical study on the certified robustness of four representative point cloud DNNs on two datasets and against seven different deformations. Compared to previous approaches for certifying point cloud DNNs, 3DeformRS is fast, scales well with point cloud size, and provides comparable-to-better certificates. For instance, when certifying a plain PointNet against a 3{\deg} z-rotation on 1024-point clouds, 3DeformRS grants a certificate 3x larger and 20x faster than previous work.
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Abstract
In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robot or vehicle navigation in general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve very efficient 3D map representation of general environment thanks to the automatic local-OGM induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalability and compactness. In addition, we also evaluate localization accuracy extensively given the created LiDAR Road-Atlas representations on several public benchmark datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization errors of 0.26m (translation) and 1.07 degrees (rotation) on the Apollo dataset, and 0.89m (translation) and 1.29 degrees (rotation) on the MulRan dataset, respectively, at 10Hz, which validates the promising performance of our map representation for autonomous driving.
Keyword: mapping
medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space
Authors: Amil Dravid, Florian Schiffers, Boqing Gong, Aggelos K. Katsaggelos
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization through latent interpolation. Furthermore, we optimize the latent space such that interpolation explains how the features contribute to the classifier's output. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability. Additionally, a combination of the medXGAN with Integrated Gradients can yield explanations more robust to noise. The code is available at: https://github.com/avdravid/medXGAN_explanations.
Generalizing Adversarial Explanations with Grad-CAM
Abstract
Gradient-weighted Class Activation Mapping (Grad- CAM), is an example-based explanation method that provides a gradient activation heat map as an explanation for Convolution Neural Network (CNN) models. The drawback of this method is that it cannot be used to generalize CNN behaviour. In this paper, we present a novel method that extends Grad-CAM from example-based explanations to a method for explaining global model behaviour. This is achieved by introducing two new metrics, (i) Mean Observed Dissimilarity (MOD) and (ii) Variation in Dissimilarity (VID), for model generalization. These metrics are computed by comparing a Normalized Inverted Structural Similarity Index (NISSIM) metric of the Grad-CAM generated heatmap for samples from the original test set and samples from the adversarial test set. For our experiment, we study adversarial attacks on deep models such as VGG16, ResNet50, and ResNet101, and wide models such as InceptionNetv3 and XceptionNet using Fast Gradient Sign Method (FGSM). We then compute the metrics MOD and VID for the automatic face recognition (AFR) use case with the VGGFace2 dataset. We observe a consistent shift in the region highlighted in the Grad-CAM heatmap, reflecting its participation to the decision making, across all models under adversarial attacks. The proposed method can be used to understand adversarial attacks and explain the behaviour of black box CNN models for image analysis.
FSOINet: Feature-Space Optimization-Inspired Network for Image Compressive Sensing
Authors: Wenjun Chen, Chunling Yang, Xin Yang
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
In recent years, deep learning-based image compressive sensing (ICS) methods have achieved brilliant success. Many optimization-inspired networks have been proposed to bring the insights of optimization algorithms into the network structure design and have achieved excellent reconstruction quality with low computational complexity. But they keep the information flow in pixel space as traditional algorithms by updating and transferring the image in pixel space, which does not fully use the information in the image features. In this paper, we propose the idea of achieving information flow phase by phase in feature space and design a Feature-Space Optimization-Inspired Network (dubbed FSOINet) to implement it by mapping both steps of proximal gradient descent algorithm from pixel space to feature space. Moreover, the sampling matrix is learned end-to-end with other network parameters. Experiments show that the proposed FSOINet outperforms the existing state-of-the-art methods by a large margin both quantitatively and qualitatively. The source code is available on https://github.com/cwjjun/FSOINet.
Fully End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-Agent
Abstract
Focusing on the task of point-to-point navigation for an autonomous driving vehicle, we propose a novel deep learning model trained with end-to-end and multi-task learning manners to perform both perception and control tasks simultaneously. The model is used to drive the ego vehicle safely by following a sequence of routes defined by the global planner. The perception part of the model is used to encode high-dimensional observation data provided by an RGBD camera while performing semantic segmentation, semantic depth cloud (SDC) mapping, and traffic light state and stop sign prediction. Then, the control part decodes the encoded features along with additional information provided by GPS and speedometer to predict waypoints that come with a latent feature space. Furthermore, two agents are employed to process these outputs and make a control policy that determines the level of steering, throttle, and brake as the final action. The model is evaluated on CARLA simulator with various scenarios made of normal-adversarial situations and different weathers to mimic real-world conditions. In addition, we do a comparative study with some recent models to justify the performance in multiple aspects of driving. Moreover, we also conduct an ablation study on SDC mapping and multi-agent to understand their roles and behavior. As a result, our model achieves the highest driving score even with fewer parameters and computation load. To support future studies, we share our codes at https://github.com/oskarnatan/end-to-end-driving.
Perception of Mechanical Properties via Wrist Haptics: Effects of Feedback Congruence
Authors: Mine Sarac, Massimiliano di Luca, Allison M. Okamura
Abstract
Despite non-co-location, haptic stimulation at the wrist can potentially provide feedback regarding interactions at the fingertips without encumbering the user's hand. Here we investigate how two types of skin deformation at the wrist (normal and shear) relate to the perception of the mechanical properties of virtual objects. We hypothesized that a congruent mapping between force at the fingertips and deformation at the wrist would be better, i.e. mapping finger normal force to skin indentation at the wrist, and shear force to skin shear at the wrist, would result in better perception than other mappings that either mixed or merged the two direction into a single type of feedback. We performed an experiment where haptic devices at the wrist rendered either normal or shear feedback during manipulation of virtual objects with varying stiffness, mass, or friction properties. Perception of mechanical properties was more accurate with congruent skin stimulation than noncongruent. In addition, discrimination performance and subjective reports were positively influenced by congruence. This study demonstrates that users can perceive mechanical properties via haptic feedback provided at the wrist with a consistent mapping between haptic feedback and interaction forces at the fingertips, regardless of congruence.
Three-Stream Joint Network for Zero-Shot Sketch-Based Image Retrieval
Abstract
The Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging task because of the large domain gap between sketches and natural images as well as the semantic inconsistency between seen and unseen categories. Previous literature bridges seen and unseen categories by semantic embedding, which requires prior knowledge of the exact class names and additional extraction efforts. And most works reduce domain gap by mapping sketches and natural images into a common high-level space using constructed sketch-image pairs, which ignore the unpaired information between images and sketches. To address these issues, in this paper, we propose a novel Three-Stream Joint Training Network (3JOIN) for the ZS-SBIR task. To narrow the domain differences between sketches and images, we extract edge maps for natural images and treat them as a bridge between images and sketches, which have similar content to images and similar style to sketches. For exploiting a sufficient combination of sketches, natural images, and edge maps, a novel three-stream joint training network is proposed. In addition, we use a teacher network to extract the implicit semantics of the samples without the aid of other semantics and transfer the learned knowledge to unseen classes. Extensive experiments conducted on two real-world datasets demonstrate the superiority of our proposed method.
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Abstract
In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robot or vehicle navigation in general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve very efficient 3D map representation of general environment thanks to the automatic local-OGM induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalability and compactness. In addition, we also evaluate localization accuracy extensively given the created LiDAR Road-Atlas representations on several public benchmark datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization errors of 0.26m (translation) and 1.07 degrees (rotation) on the Apollo dataset, and 0.89m (translation) and 1.29 degrees (rotation) on the MulRan dataset, respectively, at 10Hz, which validates the promising performance of our map representation for autonomous driving.
Membership-Mappings for Practical Secure Distributed Deep Learning
Authors: Mohit Kumar, Weiping Zhang, Lukas Fischer, Bernhard Freudenthaler
Abstract
This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption. The impracticality issue of secure machine (deep) learning with fully homomorphic encrypted data, arising from large computational overhead, is addressed via applying fuzzy attributes. Fuzzy attributes are induced by globally convergent and robust variational membership-mappings based local deep models. Fuzzy attributes combine the local deep models in a robust and flexible manner such that the global model can be evaluated homomorphically in an efficient manner using a boolean circuit composed of bootstrapped binary gates. The proposed method, while preserving privacy in a distributed learning scenario, remains accurate, practical, and scalable. The method is evaluated through numerous experiments including demonstrations through MNIST dataset and Freiburg Groceries Dataset. Further, a biomedical application related to mental stress detection on individuals is considered.
Keyword: localization
medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space
Authors: Amil Dravid, Florian Schiffers, Boqing Gong, Aggelos K. Katsaggelos
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization through latent interpolation. Furthermore, we optimize the latent space such that interpolation explains how the features contribute to the classifier's output. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability. Additionally, a combination of the medXGAN with Integrated Gradients can yield explanations more robust to noise. The code is available at: https://github.com/avdravid/medXGAN_explanations.
Fault Detection and Localization in Active Distribution Networks using Optimally Placed Phasor Measurements Units
Authors: Francesco Conte, Fabio D'Agostino, Bruno Gabriele, Giacomo-Piero Schiapparelli, Federico Silvestro
Abstract
This paper introduces an algorithm able to detect and localize the occurrance of a fault in an Active Distribution Network, using the measurements collected by Phasor Measurement Units (PMUs). First, a basic algorithm that works under the assumption that all grid buses are equipped with a PMU is designed. Then, formal observability conditions that allow detection and localization with a reduced number of PMUs are provided. Based on these conditions, the algorithm is extended to perform correctly when not all network buses are monitored. Moreover, an Optimal Positioning Algorithm, always based on the observability conditions, is designed. This algorithm allows the user to customize the fault localization resolution. The approach is validated through simulations carried out on a benchmark active distribution network.
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Abstract
In this work, we propose the LiDAR Road-Atlas, a compactable and efficient 3D map representation, for autonomous robot or vehicle navigation in general urban environment. The LiDAR Road-Atlas can be generated by an online mapping framework based on incrementally merging local 2D occupancy grid maps (2D-OGM). Specifically, the contributions of our LiDAR Road-Atlas representation are threefold. First, we solve the challenging problem of creating local 2D-OGM in non-structured urban scenes based on a real-time delimitation of traversable and curb regions in LiDAR point cloud. Second, we achieve accurate 3D mapping in multiple-layer urban road scenarios by a probabilistic fusion scheme. Third, we achieve very efficient 3D map representation of general environment thanks to the automatic local-OGM induced traversable-region labeling and a sparse probabilistic local point-cloud encoding. Given the LiDAR Road-Atlas, one can achieve accurate vehicle localization, path planning and some other tasks. Our map representation is insensitive to dynamic objects which can be filtered out in the resulting map based on a probabilistic fusion. Empirically, we compare our map representation with a couple of popular map representation methods in robotics and autonomous driving societies, and our map representation is more favorable in terms of efficiency, scalability and compactness. In addition, we also evaluate localization accuracy extensively given the created LiDAR Road-Atlas representations on several public benchmark datasets. With a 16-channel LiDAR sensor, our method achieves an average global localization errors of 0.26m (translation) and 1.07 degrees (rotation) on the Apollo dataset, and 0.89m (translation) and 1.29 degrees (rotation) on the MulRan dataset, respectively, at 10Hz, which validates the promising performance of our map representation for autonomous driving.
Abstract
Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the classification logits due to its inefficiency in distilling the localization information. In this paper, we investigate whether logit mimicking always lags behind feature imitation. Towards this goal, we first present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. Second, we introduce the concept of valuable localization region that can aid to selectively distill the classification and localization knowledge for a certain region. Combining these two new components, for the first time, we show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years. The thorough studies exhibit the great potential of logit mimicking that can significantly alleviate the localization ambiguity, learn robust feature representation, and ease the training difficulty in the early stage. We also provide the theoretical connection between the proposed LD and the classification KD, that they share the equivalent optimization effect. Our distillation scheme is simple as well as effective and can be easily applied to both dense horizontal object detectors and rotated object detectors. Extensive experiments on the MS COCO, PASCAL VOC, and DOTA benchmarks demonstrate that our method can achieve considerable AP improvement without any sacrifice on the inference speed. Our source code and pretrained models are publicly available at https://github.com/HikariTJU/LD.
Keyword: SLAM
RGB-D Semantic SLAM for Surgical Robot Navigation in the Operating Room
HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
Keyword: Visual inertial
There is no result
Keyword: livox
There is no result
Keyword: loam
There is no result
Keyword: Visual inertial odometry
There is no result
Keyword: lidar
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
EVOPS Benchmark: Evaluation of Plane Segmentation from RGBD and LiDAR Data
Keyword: loop detection
There is no result
Keyword: autonomous driving
Fully End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-Agent
DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection
3DeformRS: Certifying Spatial Deformations on Point Clouds
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Keyword: mapping
medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space
Generalizing Adversarial Explanations with Grad-CAM
FSOINet: Feature-Space Optimization-Inspired Network for Image Compressive Sensing
Fully End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-Agent
Perception of Mechanical Properties via Wrist Haptics: Effects of Feedback Congruence
Three-Stream Joint Network for Zero-Shot Sketch-Based Image Retrieval
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Membership-Mappings for Practical Secure Distributed Deep Learning
Keyword: localization
medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space
Fault Detection and Localization in Active Distribution Networks using Optimally Placed Phasor Measurements Units
LiDAR Road-Atlas: An Efficient Map Representation for General 3D Urban Environment
Localization Distillation for Object Detection