G2LL: Global-To-Local Self-Supervised Learning for Label-Efficient Transformer-Based Skin Lesion Segmentation in Dermoscopy Images - IMT Mines Alès Access content directly
Conference Papers Year : 2023

G2LL: Global-To-Local Self-Supervised Learning for Label-Efficient Transformer-Based Skin Lesion Segmentation in Dermoscopy Images

Fei Chen
  • Function : Author
Jiacheng Wang
  • Function : Author
Baptiste Magnier
Wei Xue
  • Function : Author
Shaohui Huang
  • Function : Author
Liansheng Wang
  • Function : Author

Abstract

Skin lesion segmentation in dermoscopy images is highly relevant for lesion assessment and subsequent analysis. Recently, automatic transformer-based skin lesion segmentation models have achieved high segmentation accuracy owing to their long-range modeling capability. However, limited labeled data for training the lesion segmentation models results in sub-optimal learning results. In this paper, we propose a Global-to-Local self-supervised Learning (G2LL) method for transformer-based skin lesion segmentation models to alleviate the problem of insufficient annotated data. Firstly, a structure-wise masking strategy for Masked Image Modeling (MIM) is proposed to force the model to learn the reconstruction of masked structures by exploring the semantic local contexts. Instead of masking patches randomly in the whole view, it computes super-pixels to divide the images into several structured regions. Then, it masks the fixed number of patches in each region, thus it allows the exploration of the structural knowledge and solves the shape variance in the meanwhile. Secondly, a self-distilling architecture is deployed to enhance global context learning where the masked images are sent to a student network and the relative unmasked images are fed to a teacher network for knowledge distillation. In this context, extensive experiments on both the ISIC-2017 and the ISIC-2019 datasets containing a total of 28081 images show that the proposed approach is superior to state-of-the-art self-supervised learning methods
Fichier principal
Vignette du fichier
g2ll-global-to-local-self-supervised.pdf (2.75 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04205226 , version 1 (10-06-2024)

Identifiers

Cite

Fei Chen, Jiacheng Wang, Baptiste Magnier, Wei Xue, Shaohui Huang, et al.. G2LL: Global-To-Local Self-Supervised Learning for Label-Efficient Transformer-Based Skin Lesion Segmentation in Dermoscopy Images. ISBI 2023 - IEEE 20th International Symposium on Biomedical Imaging, Apr 2023, Cartagena de Indias, Colombia. pp.1-5, ⟨10.1109/ISBI53787.2023.10230748⟩. ⟨hal-04205226⟩
15 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More