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
  • [31] ViewMix: Augmentation for Robust Representation in Self-Supervised Learning
    Das, Arjon
    Zhong, Xin
    IEEE ACCESS, 2024, 12 : 8461 - 8470
  • [32] Randomly shuffled convolution for self-supervised representation learning
    Oh, Youngjin
    Jeon, Minkyu
    Ko, Dohwan
    Kim, Hyunwoo J.
    INFORMATION SCIENCES, 2023, 623 : 206 - 219
  • [33] Self-supervised representation learning for surgical activity recognition
    Paysan, Daniel
    Haug, Luis
    Bajka, Michael
    Oelhafen, Markus
    Buhmann, Joachim M.
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2021, 16 (11) : 2037 - 2044
  • [34] AtmoDist: Self-supervised representation learning for atmospheric dynamics
    Hoffmann, Sebastian
    Lessig, Christian
    ENVIRONMENTAL DATA SCIENCE, 2023, 2
  • [35] Heuristic Attention Representation Learning for Self-Supervised Pretraining
    Van Nhiem Tran
    Liu, Shen-Hsuan
    Li, Yung-Hui
    Wang, Jia-Ching
    SENSORS, 2022, 22 (14)
  • [36] Phonetically Motivated Self-Supervised Speech Representation Learning
    Yue, Xianghu
    Li, Haizhou
    INTERSPEECH 2021, 2021, : 746 - 750
  • [37] SELF-SUPERVISED REPRESENTATION LEARNING FROM ELECTROENCEPHALOGRAPHY SIGNALS
    Banville, Hubert
    Albuquerque, Isabela
    Hyvarinen, Aapo
    Moffat, Graeme
    Engemann, Denis-Alexander
    Gramfort, Alexandre
    2019 IEEE 29TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2019,
  • [38] Random Field Augmentations for Self-Supervised Representation Learning
    Mansfield, Philip Andrew
    Afkanpour, Arash
    Morningstar, Warren Richard
    Singhal, Karan
    NEURIPS WORKSHOP ON SYMMETRY AND GEOMETRY IN NEURAL REPRESENTATIONS, 2023, 228 : 292 - 302
  • [39] An Artificial Neural SLAM Framework for Event-Based Vision
    Gelen, Aykut G.
    Atasoy, Ayten
    IEEE ACCESS, 2023, 11 : 58436 - 58450
  • [40] Self-Supervised Learning With Segmental Masking for Speech Representation
    Yue, Xianghu
    Lin, Jingru
    Gutierrez, Fabian Ritter
    Li, Haizhou
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2022, 16 (06) : 1367 - 1379