EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision

被引:0
|
作者
Qu, Qiang [1 ]
Chen, Xiaoming [2 ]
Chung, Yuk Ying [1 ]
Shen, Yiran [3 ]
机构
[1] Univ Sydney, Sch Comp Sci, Sydney, NSW 2050, Australia
[2] Beijing Technol & Business Univ, Sch Comp & Artificial Intelligence, Beijing 102401, Peoples R China
[3] Shandong Univ, Sch Software, Jinan 250100, Peoples R China
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
Cameras; Event detection; Optical flow; Estimation; Self-supervised learning; Noise; Computer vision; Accuracy; Generators; Noise reduction; Dynamic vision sensor; neuromorphic vision; event camera; representation learning; event-based vision; SENSOR;
D O I
10.1109/TIP.2024.3497795
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach's superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.
引用
收藏
页码:6579 / 6591
页数:13
相关论文
共 50 条
  • [21] Self-Supervised Representation Learning for Basecalling Nanopore Sequencing Data
    Vintimilla, Carlos
    Hwang, Sangheum
    IEEE ACCESS, 2024, 12 : 109355 - 109366
  • [22] Robust Event-Based Vision Model Estimation by Dispersion Minimisation
    Nunes, Urbano Miguel
    Demiris, Yiannis
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 9561 - 9573
  • [23] Self-supervised graph representation learning via positive mining
    Lee, Namkyeong
    Lee, Junseok
    Park, Chanyoung
    INFORMATION SCIENCES, 2022, 611 : 476 - 493
  • [24] Self-Supervised Graph Representation Learning via Information Bottleneck
    Gu, Junhua
    Zheng, Zichen
    Zhou, Wenmiao
    Zhang, Yajuan
    Lu, Zhengjun
    Yang, Liang
    SYMMETRY-BASEL, 2022, 14 (04):
  • [25] Self-Supervised Lie Algebra Representation Learning via Optimal Canonical Metric
    Yu, Xiaohan
    Pan, Zicheng
    Zhao, Yang
    Gao, Yongsheng
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (02) : 3547 - 3558
  • [26] Self-Supervised Node Representation Learning via Node-to-Neighbourhood Alignment
    Dong, Wei
    Yan, Dawei
    Wang, Peng
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (06) : 4218 - 4233
  • [27] Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer
    Zhang, Wenrui
    Yang, Ling
    Geng, Shijia
    Hong, Shenda
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (11) : 16129 - 16138
  • [28] Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes
    Sun, Chao
    Zheng, Zhedong
    Wang, Xiaohan
    Xu, Mingliang
    Yang, Yi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 6207 - 6218
  • [29] Learning Adaptive Parameter Representation for Event-Based Video Reconstruction
    Gu, Daxin
    Li, Jia
    Zhu, Lin
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 1950 - 1954
  • [30] TRIBYOL: TRIPLET BYOL FOR SELF-SUPERVISED REPRESENTATION LEARNING
    Li, Guang
    Togo, Ren
    Ogawa, Takahiro
    Haseyama, Miki
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3458 - 3462