Chen, J., Chen, C., Huang, W. et al. (3 more authors) (2024) Dynamic contrastive learning guided by class confidence and confusion degree for medical image segmentation. Pattern Recognition, 145. 109881. ISSN 0031-3203
Abstract
This work proposes an intra-Class-confidence and inter-Class-confusion guided Dynamic Contrastive (CCDC) learning framework for medical image segmentation. A core contribution is to dynamically select the most expressive pixels to build positive and negative pairs for contrastive learning at different training phases. For the positive pairs, dynamically adaptive sampling strategies are introduced for sampling different sets of pixels based on their hardness (namely the easiest, easy, and hard pixels). For the negative pairs, to efficiently learn from the classes with high confusion degree w.r.t a query class (i.e., a class containing the query pixels), a new hard class mining strategy is presented. Furthermore, pixel-level representations are extended to the neighbourhood region to leverage the spatial consistency of adjacent pixels. Extensive experiments on the three public datasets demonstrate that the proposed method significantly surpasses the state-of-the-art.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 Elsevier Ltd. This is an author produced version of a paper subsequently published in Pattern Recognition. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
Keywords: | Class confusion degree; Dynamic contrastive learning; Medical image segmentation |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Sep 2023 10:27 |
Last Modified: | 16 Aug 2024 00:13 |
Status: | Published |
Publisher: | Elsevier |
Refereed: | Yes |
Identification Number: | 10.1016/j.patcog.2023.109881 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:203389 |