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
  • [41] Self-supervised Representation Learning Using 360° Data
    Li, Junnan
    Liu, Jianquan
    Wong, Yongkang
    Nishimura, Shoji
    Kankanhalli, Mohan S.
    PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 998 - 1006
  • [42] Self-Supervised Representation Learning for Document Image Classification
    Siddiqui, Shoaib Ahmed
    Dengel, Andreas
    Ahmed, Sheraz
    IEEE ACCESS, 2021, 9 : 164358 - 164367
  • [43] Self-supervised representation learning for surgical activity recognition
    Daniel Paysan
    Luis Haug
    Michael Bajka
    Markus Oelhafen
    Joachim M. Buhmann
    International Journal of Computer Assisted Radiology and Surgery, 2021, 16 : 2037 - 2044
  • [44] Video Face Clustering with Self-Supervised Representation Learning
    Sharma V.
    Tapaswi M.
    Saquib Sarfraz M.
    Stiefelhagen R.
    IEEE Transactions on Biometrics, Behavior, and Identity Science, 2020, 2 (02): : 145 - 157
  • [45] A survey on self-supervised methods for visual representation learning
    Uelwer, Tobias
    Robine, Jan
    Wagner, Stefan Sylvius
    Hoeftmann, Marc
    Upschulte, Eric
    Konietzny, Sebastian
    Behrendt, Maike
    Harmeling, Stefan
    MACHINE LEARNING, 2025, 114 (04)
  • [46] Feature Representation and Compression Methods for Event-Based Data
    Wang, Conghe
    Wang, Xia
    Yan, Changda
    Ma, Kai
    IEEE SENSORS JOURNAL, 2023, 23 (05) : 5109 - 5123
  • [47] SELF-SUPERVISED VISION TRANSFORMERS FOR JOINT SAR-OPTICAL REPRESENTATION LEARNING
    Wang, Yi
    Albrecht, Conrad M.
    Zhu, Xiao Xiang
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 139 - 142
  • [48] Towards Pointsets Representation Learning via Self-Supervised Learning and Set Augmentation
    Arsomngern, Pattaramanee
    Long, Cheng
    Suwajanakorn, Supasorn
    Nutanong, Sarana
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (01) : 1201 - 1216
  • [49] Simple Self-supervised Multiplex Graph Representation Learning
    Mo, Yujie
    Chen, Yuhuan
    Peng, Liang
    Shi, Xiaoshuang
    Zhu, Xiaofeng
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 3301 - 3309
  • [50] Meta-Learning and Self-Supervised Pretraining for Storm Event Imagery Translation
    Rugina, Ileana
    Dangovski, Rumen
    Simek, Olga
    Veillette, Mark
    Khorrami, Pooya
    Soljacic, Marin
    Cheung, Brian
    2023 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE, HPEC, 2023,