DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning

被引:0
作者
Torpey, David [1 ]
Klein, Richard [1 ]
机构
[1] Univ Witwatersrand, Sch Comp Sci & Appl Math, Johannesburg, South Africa
关键词
Deep learning; Self-supervised learning; Representation learning; Medical image analysis;
D O I
10.1016/j.patrec.2024.09.005
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Often, applications of self-supervised learning to 3D medical data opt to use 3D variants of successful 2D network architectures. Although promising approaches, they are significantly more computationally demanding to train, and thus reduce the widespread applicability of these methods away from those with modest computational resources. Thus, in this paper, we aim to improve standard 2D SSL algorithms by modelling the inherent 3D nature of these datasets implicitly. We propose two variants that build upon a strong baseline model and show that both of these variants often outperform the baseline in a variety of downstream tasks. Importantly, in contrast to previous works in both 2D and 3D approaches for 3D medical data, both of our proposals introduce negligible additional overhead in terms of parameter complexity. Although data loading overhead increases over the baseline SimCLR model (which we can show can be somewhat mitigated through parallelisation), our proposed models are still significantly more efficient than previous approaches based on sequence modelling. Overall, our proposed methods help improve the democratisation of these approaches for medical applications.
引用
收藏
页码:64 / 70
页数:7
相关论文
共 50 条
  • [41] Collaboratively Self-Supervised Video Representation Learning for Action Recognition
    Zhang, Jie
    Wan, Zhifan
    Hu, Lanqing
    Lin, Stephen
    Wu, Shuzhe
    Shan, Shiguang
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 20 : 1895 - 1907
  • [42] Efficient self-supervised heterogeneous graph representation learning with reconstruction
    Mo, Yujie
    Shen, Heng Tao
    Zhu, Xiaofeng
    INFORMATION FUSION, 2025, 117
  • [43] 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
  • [44] Dense Semantic Contrast for Self-Supervised Visual Representation Learning
    Li, Xiaoni
    Zhou, Yu
    Zhang, Yifei
    Zhang, Aoting
    Wang, Wei
    Jiang, Ning
    Wu, Haiying
    Wang, Weiping
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 1368 - 1376
  • [45] Augmentation Adversarial Training for Self-Supervised Speaker Representation Learning
    Kang, Jingu
    Huh, Jaesung
    Heo, Hee Soo
    Chung, Joon Son
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2022, 16 (06) : 1253 - 1262
  • [46] Contrastive Self-supervised Representation Learning Using Synthetic Data
    Dong-Yu She
    Kun Xu
    International Journal of Automation and Computing, 2021, 18 (04) : 556 - 567
  • [47] Contrastive Self-supervised Representation Learning Using Synthetic Data
    Dong-Yu She
    Kun Xu
    International Journal of Automation and Computing, 2021, 18 : 556 - 567
  • [48] Audio-visual self-supervised representation learning: A survey
    Alsuwat, Manal
    Al-Shareef, Sarah
    Alghamdi, Manal
    NEUROCOMPUTING, 2025, 634
  • [49] Self-Supervised Learning for Videos: A Survey
    Schiappa, Madeline C.
    Rawat, Yogesh S.
    Shah, Mubarak
    ACM COMPUTING SURVEYS, 2023, 55 (13S)
  • [50] A New Deep Learning Method with Self-Supervised Learning for Delineation of the Electrocardiogram
    Wu, Wenwen
    Huang, Yanqi
    Wu, Xiaomei
    ENTROPY, 2022, 24 (12)