Abstract
Object detection is a computer vision task that has become an integral part of many consumer applications today such as surveillance and security systems, mobile text recognition, and diagnosing diseases from MRI/CT scans. Object detection is also one of the critical components to support autonomous driving. Autonomous vehicles rely on the perception of their surroundings to ensure safe and robust driving performance. This perception system uses object detection algorithms to accurately determine objects such as pedestrians, vehicles, traffic signs, and barriers in the vehicle's vicinity. Deep learning-based object detectors play a vital role in finding and localizing these objects in real-time. This article discusses the state-of-the-art in object detectors and open challenges for their integration into autonomous vehicles.
Keyword: mapping
Poseur: Direct Human Pose Regression with Transformers
Authors: Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton van den Hengel
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
ReconROS Executor: Event-Driven Programming of FPGA-accelerated ROS 2 Applications
Abstract
Many applications from the robotics domain can benefit from FPGA acceleration. A corresponding key question is how to integrate hardware accelerators into software-centric robotics programming environments. Recently, several approaches have demonstrated hardware acceleration for the robot operating system (ROS), the dominant programming environment in robotics. ROS is a middleware layer that features the composition of complex robotics applications as a set of nodes that communicate via mechanisms such as publish/subscribe, and distributes them over several compute platforms. In this paper, we present a novel approach for event-based programming of robotics applications that leverages ReconROS, a framework for flexibly mapping ROS 2 nodes to either software or reconfigurable hardware. The ReconROS executor schedules callbacks of ROS 2 nodes and utilizes a reconfigurable slot model and partial runtime reconfiguration to load hardware-based callbacks on demand. We describe the ReconROS executor approach, give design examples, and experimentally evaluate its functionality with examples.
CyberRadar: A PUF-based Detecting and Mapping Framework for Physical Devices
Authors: Dawei Li, Di Liu, Yangkun Ren, Ziyi Wang, Yu Sun, Zhenyu Guan, Qianhong Wu, Jianwei Liu
Abstract
The core issue of cyberspace detecting and mapping is to accurately identify and dynamically track devices. However, with the development of anonymization technology, devices can have multiple IP addresses and MAC addresses, and it is difficult to map multiple virtual attributes to the same physical device by existing detecting and mapping technologies. In this paper, we propose a detailed PUF-based detecting and mapping framework which can actively detect physical resources in cyberspace, construct resource portraits based on physical fingerprints, and dynamically track devices. We present a new method to implement a rowhammer DRAM PUF on a general PC equipped with DDR4 memory. The PUF performance evaluation shows that the extracted rowhammer PUF response is unique and reliable on PC, which can be treated as the device's unique physical fingerprint. The results of detecting and mapping experiments show that the framework we proposed can accurately identify the target devices. Even if the device modifies its MAC address, IP address, and operating system, by constructing a physical fingerprint database for device matching, the identification accuracy is close to the ideal value of 100%.
CAST: Character labeling in Animation using Self-supervision by Tracking
Authors: Oron Nir, Gal Rapoport, Ariel Shamir
Subjects: Computer Vision and Pattern Recognition (cs.CV)
Abstract
Cartoons and animation domain videos have very different characteristics compared to real-life images and videos. In addition, this domain carries a large variability in styles. Current computer vision and deep-learning solutions often fail on animated content because they were trained on natural images. In this paper we present a method to refine a semantic representation suitable for specific animated content. We first train a neural network on a large-scale set of animation videos and use the mapping to deep features as an embedding space. Next, we use self-supervision to refine the representation for any specific animation style by gathering many examples of animated characters in this style, using a multi-object tracking. These examples are used to define triplets for contrastive loss training. The refined semantic space allows better clustering of animated characters even when they have diverse manifestations. Using this space we can build dictionaries of characters in an animation videos, and define specialized classifiers for specific stylistic content (e.g., characters in a specific animation series) with very little user effort. These classifiers are the basis for automatically labeling characters in animation videos. We present results on a collection of characters in a variety of animation styles.
FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks
Authors: Shien Zhu, Luan H.K. Duong, Hui Chen, Di Liu, Weichen Liu
Abstract
Convolutional Neural Networks (CNNs) demonstrate great performance in various applications but have high computational complexity. Quantization is applied to reduce the latency and storage cost of CNNs. Among the quantization methods, Binary and Ternary Weight Networks (BWNs and TWNs) have a unique advantage over 8-bit and 4-bit quantization. They replace the multiplication operations in CNNs with additions, which are favoured on In-Memory-Computing (IMC) devices. IMC acceleration for BWNs has been widely studied. However, though TWNs have higher accuracy and better sparsity, IMC acceleration for TWNs has limited research. TWNs on existing IMC devices are inefficient because the sparsity is not well utilized, and the addition operation is not efficient. In this paper, we propose FAT as a novel IMC accelerator for TWNs. First, we propose a Sparse Addition Control Unit, which utilizes the sparsity of TWNs to skip the null operations on zero weights. Second, we propose a fast addition scheme based on the memory Sense Amplifier to avoid the time overhead of both carry propagation and writing back the carry to the memory cells. Third, we further propose a Combined-Stationary data mapping to reduce the data movement of both activations and weights and increase the parallelism of memory columns. Simulation results show that for addition operations at the Sense Amplifier level, FAT achieves 2.00X speedup, 1.22X power efficiency and 1.22X area efficiency compared with State-Of-The-Art IMC accelerator ParaPIM. FAT achieves 10.02X speedup and 12.19X energy efficiency compared with ParaPIM on networks with 80% sparsity
Problem examination for AI methods in product design
Abstract
Artificial Intelligence (AI) has significant potential for product design: AI can check technical and non-technical constraints on products, it can support a quick design of new product variants and new AI methods may also support creativity. But currently product design and AI are separate communities fostering different terms and theories. This makes a mapping of AI approaches to product design needs difficult and prevents new solutions. As a solution, this paper first clarifies important terms and concepts for the interdisciplinary domain of AI methods in product design. A key contribution of this paper is a new classification of design problems using the four characteristics decomposability, inter-dependencies, innovation and creativity. Definitions of these concepts are given where they are lacking. Early mappings of these concepts to AI solutions are sketched and verified using design examples. The importance of creativity in product design and a corresponding gap in AI is pointed out for future research.
Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
Authors: Apostolos F Psaros, Xuhui Meng, Zongren Zou, Ling Guo, George Em Karniadakis
Abstract
Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with traditional methods. However, quantifying errors and uncertainties in NN-based inference is more complicated than in traditional methods. This is because in addition to aleatoric uncertainty associated with noisy data, there is also uncertainty due to limited data, but also due to NN hyperparameters, overparametrization, optimization and sampling errors as well as model misspecification. Although there are some recent works on uncertainty quantification (UQ) in NNs, there is no systematic investigation of suitable methods towards quantifying the total uncertainty effectively and efficiently even for function approximation, and there is even less work on solving partial differential equations and learning operator mappings between infinite-dimensional function spaces using NNs. In this work, we present a comprehensive framework that includes uncertainty modeling, new and existing solution methods, as well as evaluation metrics and post-hoc improvement approaches. To demonstrate the applicability and reliability of our framework, we present an extensive comparative study in which various methods are tested on prototype problems, including problems with mixed input-output data, and stochastic problems in high dimensions. In the Appendix, we include a comprehensive description of all the UQ methods employed, which we will make available as open-source library of all codes included in this framework.
Keyword: SLAM
There is no result
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
There is no result
Keyword: loop detection
There is no result
Keyword: autonomous driving
Object Detection in Autonomous Vehicles: Status and Open Challenges
Keyword: mapping
Poseur: Direct Human Pose Regression with Transformers
ReconROS Executor: Event-Driven Programming of FPGA-accelerated ROS 2 Applications
CyberRadar: A PUF-based Detecting and Mapping Framework for Physical Devices
CAST: Character labeling in Animation using Self-supervision by Tracking
FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks
Problem examination for AI methods in product design
Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
Keyword: localization
There is no result