检索结果-内蒙古大学图书馆

Mixture of Attention Heads: Selecting Attention Heads Per Token

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Xiaofeng Shen, Yikang Huang, Zeyu Zhou, Jie Rong, Wenge Xiong, Zhang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University China Sino-French Engineer School Beihang University China Mila University of Montreal Canada Wechat AI Tencent China

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer architecture. This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism. MoA includes a set of attention heads that each has its own set of parameters. Given an input, a router dynamically selects a subset of k attention heads per token. This conditional computation schema allows MoA to achieve stronger performance than the standard multi-head attention layer. Furthermore, the sparsely gated MoA can easily scale up the number of attention heads and the number of parameters while preserving computational efficiency. In addition to the performance improvements, MoA also automatically differentiates heads’ utilities, providing a new perspective to discuss the model’s interpretability. We conducted experiments on several important tasks, including Machine Translation and Masked Language Modeling. Experiments have shown promising results on several tasks against strong baselines that involve large and very deep models. Copyright © 2022, The Authors. All rights reserved.

关键词： Mixtures

Challenges and countermeasures of interaction in autonomous vehicles

学校读者我要写书评

暂无评论

science China(Information sciences) 2019年第5期62卷 5-7页

作者： Deyi LI Meng LIU Fei ZHAO Yu LIU State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University Chinese Academy of Engineering School of Transportation Science and Engineering Beihang University

Autonomous vehicles can bring changes into ways of traveling, traffic, and even production modes [1].At present, the majority of researches [2] on autonomous vehicles are limited in perception, planning, decision-making and other calculation front,while interactive cognitive perspective is barely looked into. The interactive sector involved in self-driving is rather sophisticated [3]. However,

关键词： Challenges and countermeasures of interaction in autonomous vehicles

Deep Common Feature Mining for Efficient Video Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Yaoyan Yang, Hongyu Huang, Di State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai201112 China Zhejiang Industrial Big Data and Robot Intelligent System Key Laboratory Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation process, underscore the need for further innovation. In response, we present Deep Common Feature Mining (DCFM), a novel approach strategically designed to address these challenges by leveraging the concept of feature sharing. DCFM explicitly decomposes features into two complementary components. The common representation extracted from a key-frame furnishes essential high-level information to neighboring non-key frames, allowing for direct re-utilization without feature propagation. Simultaneously, the independent feature, derived from each video frame, captures rapidly changing information, providing frame-specific clues crucial for segmentation. To achieve such decomposition, we employ a symmetric training strategy tailored for sparsely annotated data, empowering the backbone to learn a robust high-level representation enriched with common information. Additionally, we incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency. Experimental evaluations on the VSPW and Cityscapes datasets demonstrate the effectiveness of our method, showing a superior balance between accuracy and efficiency. The implementation is availab.e at https://***/BUAAHugeGun/DCFM. © 2024, CC BY-NC-SA.

关键词： Semantic Segmentation

Perspective, survey and trends: Public driving datasets and toolsets for autonomous driving virtual test

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ji, Pengliang Ruan, Li Xiao, Limin Xue, Yunzhi Dong, Qian State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Owing to the merits of early safety and reliability guarantee, autonomous driving virtual testing has recently gains increasing attention compared with closed-loop testing in real scenarios. Although the availab.lity and quality of autonomous driving datasets and toolsets are the premise to diagnose the autonomous driving system bottlenecks and improve the system performance, due to the diversity and privacy of the datasets and toolsets, collecting and featuring the perspective and quality of them become not only time-consuming but also increasingly challenging. This paper first proposes a Systematic Literature review approach for Autonomous driving tests (SLA), then presents an overview of existing publicly availab.e datasets and toolsets from 2000 to 2020. Quantitative findings with the scenarios concerned, perspectives and trend inferences and suggestions with 35 automated driving test tool sets and 70 test data sets are also presented. To the best of our knowledge, we are the first to perform such recent empirical survey on both the datasets and toolsets using a SLA based survey approach. Our multifaceted analyses and new findings not only reveal insights that we believe are useful for system designers, practitioners and users, but also can promote more researches on a systematic survey analysis in autonomous driving surveys on dataset and toolsets. Copyright © 2021, The Authors. All rights reserved.

关键词： Surveys

Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Bing Chen, Jiaxin Zhang, Dongming Bao, Xiuguo Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China

Compressed video action recognition has recently drawn growing attention, since it remarkably reduces the storage and computational cost via replacing raw videos by sparsely sampled RGB frames and compressed motion cues (e.g., motion vectors and residuals). However, this task severely suffers from the coarse and noisy dynamics and the insufficient fusion of the heterogeneous RGB and motion modalities. To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net). It follows the two-stream architecture, i.e. one for the RGB modality and the other for the motion modality. Particularly, the motion stream employs a multi-scale block embedded with a denoising module to enhance representation learning. The interaction between the two streams is then strengthened by introducing the Selective Motion Complement (SMC) and Cross-Modality Augment (CMA) modules, where SMC complements the RGB modality with spatio-temporally attentive local motion features and CMA further combines the two modalities with selective feature augmentation. Extensive experiments on the UCF-101, HMDB-51 and Kinetics-400 benchmarks demonstrate the effectiveness and efficiency of MEACI-Net. © 2022, CC BY.

关键词： Image compression

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Guodong Wang, Yunhong Qin, Jie Zhang, Dongming Bao, Xiuguo Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China College of Computer Science and Technology NUAA Nanjing China Natl. Comp. Net. Emer. Resp. Tech. Team/Coord. Ctr. of China Beijing China

Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications. Though recent self-supervised learning based attempts achieve promising results by creating virtual outliers, their training objectives are less faithful to AD which requires a concentrated inlier distribution as well as a dispersive outlier distribution. In this paper, we propose Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation (UniCon-HA), taking into account both the requirements above. Specifically, we explicitly encourage the concentration of inliers and the dispersion of virtual outliers via supervised and unsupervised contrastive losses, respectively. Considering that standard contrastive data augmentation for generating positive views may induce outliers, we additionally introduce a soft mechanism to re-weight each augmented inlier according to its deviation from the inlier distribution, to ensure a purified concentration. Moreover, to prompt a higher concentration, inspired by curriculum learning, we adopt an easy-to-hard hierarchical augmentation strategy and perform contrastive aggregation at different depths of the network based on the strengths of data augmentation. Our method is evaluated under three AD settings including unlab.led one-class, unlab.led multi-class, and lab.led multi-class, demonstrating its consistent superiority over other competitors. © 2023, CC BY-NC-SA.

关键词： Anomaly detection

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

学校读者我要写书评

暂无评论

Unilaterally Aggregated Contrastive Learning with Hierarchic...

International Conference on computer Vision (ICCV)

作者： Guodong Wang Yunhong Wang Jie Qin Dongming Zhang Xiuguo Bao Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China College of Computer Science and Technology NUAA Nanjing China Natl. Comp. Net. Emer. Resp. Tech. Team/Coord. Ctr. of China Beijing China

关键词：

Double-Dot Network for antipodal grasp detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yao Zheng, Yangtao Gao, Boyang Di Huang The State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China The Geometry Robotics

This paper proposes a new deep learning approach to antipodal grasp detection, named Double-Dot Network (DD-Net). It follows the recent anchor-free object detection framework, which does not depend on empirically pre-set anchors and thus allows more generalized and flexible prediction on unseen objects. Specifically, unlike the widely used 5-dimensional rectangle, the gripper configuration is defined as a pair of fingertips. An effective CNN architecture is introduced to localize such fingertips, and with the help of auxiliary centers for refinement, it accurately and robustly infers grasp candidates. Additionally, we design a specialized loss function to measure the quality of grasps, and in contrast to the IoU scores of bounding boxes adopted in object detection, it is more consistent to the grasp detection task. Both the simulation and robotic experiments are executed and state of the art accuracies are achieved, showing that DD-Net is superior to the counterparts in handling unseen objects. © 2021, CC BY.

关键词： Object recognition

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Kaicheng Yang, Hongyu Chen, Binghui Li, Pengyu Wang, Biao Huang, Di State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Institute of Artificial Intelligence Beihang University China Hangzhou Innovation Institute Beihang University China

Along with the widespread use of face recognition systems, their vulnerability has become highlighted. While existing face anti-spoofing methods can be generalized between attack types, generic solutions are still challenging due to the diversity of spoof characteristics. Recently, the spoof trace disentanglement framework has shown great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement model which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling network is designed to estimate spoof patterns from the RGB and depth inputs, respectively. In this case, it captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement in each individual modality. It then performs cross-modality aggregation to deliver a more comprehensive spoof trace representation for prediction. Extensive evaluations are conducted on multiple benchmarks, demonstrating that learning polysemantic spoof traces favorably contributes to anti-spoofing with more perceptible and interpretable results. © 2022, CC BY-NC-SA.

关键词： Face recognition