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
中国国家自然科学基金; 北京市自然科学基金;
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
  • [1] Self-Supervised High-Order Information Bottleneck Learning of Spiking Neural Network for Robust Event-Based Optical Flow Estimation
    Yang, Shuangming
    Linares-Barranco, Bernabe
    Wu, Yuzhu
    Chen, Badong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 47 (04) : 2280 - 2297
  • [2] Self-supervised learning representation for abnormal acoustic event detection based on attentional contrastive learning
    Wei, Juan
    Zhang, Qian
    Ning, Weichen
    DIGITAL SIGNAL PROCESSING, 2023, 142
  • [3] FEDERATED SELF-SUPERVISED LEARNING FOR ACOUSTIC EVENT CLASSIFICATION
    Feng, Meng
    Kao, Chieh-Chi
    Tang, Qingming
    Sun, Ming
    Rozgic, Viktor
    Matsoukas, Spyros
    Wang, Chao
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 481 - 485
  • [4] CSTR: A Compact Spatio-Temporal Representation for Event-Based Vision
    El Shair, Zaid A.
    Hassani, Ali
    Rawashdeh, Samir A.
    IEEE ACCESS, 2023, 11 : 102899 - 102916
  • [5] Event Anonymization: Privacy-Preserving Person Re-Identification and Pose Estimation in Event-Based Vision
    Ahmad, Shafiq
    Morerio, Pietro
    Del Bue, Alessio
    IEEE ACCESS, 2024, 12 : 66964 - 66980
  • [6] Representation learning using event-based STDP
    Tavanaei, Amirhossein
    Masquelier, Timothee
    Maida, Anthony
    NEURAL NETWORKS, 2018, 105 : 294 - 303
  • [7] Event-LSTM: An Unsupervised and Asynchronous Learning-Based Representation for Event-Based Data
    Annamalai, Lakshmi
    Ramanathan, Vignesh
    Thakur, Chetan Singh
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02): : 4678 - 4685
  • [8] Self-Supervised Graph Representation Learning via Topology Transformations
    Gao, Xiang
    Hu, Wei
    Qi, Guo-Jun
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (04) : 4202 - 4215
  • [9] Self-Supervised Visual Representation Learning via Residual Momentum
    Pham, Trung Xuan
    Niu, Axi
    Zhang, Kang
    Jin, Tee Joshua Tian
    Hong, Ji Woo
    Yoo, Chang D.
    IEEE ACCESS, 2023, 11 : 116706 - 116720
  • [10] Functional Knowledge Transfer with Self-supervised Representation Learning
    Chhipa, Prakash Chandra
    Chopra, Muskaan
    Mengi, Gopal
    Gupta, Varun
    Upadhyay, Richa
    Chippa, Meenakshi Subhash
    De, Kanjar
    Saini, Rajkumar
    Uchida, Seiichi
    Liwicki, Marcus
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 3339 - 3343