Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.18147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910663814676480 |
|---|---|
| author | Ye, Mengwen Huangfu, Yingzi Li, You Yu, Zekuan |
| author_facet | Ye, Mengwen Huangfu, Yingzi Li, You Yu, Zekuan |
| contents | Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-Supervised Pre-training with Robust Adaptive Credal Loss (SSP-RACL), for handling label noise in fundus image datasets. First, we use Masked Autoencoders (MAE) for pre-training to extract features, unaffected by label noise. Subsequently, RACL employ a superset learning framework, setting confidence thresholds and adaptive label relaxation parameter to construct possibility distributions and provide more reliable ground-truth estimates, thus effectively suppressing the memorization effect. Additionally, we introduce clinical knowledge-based asymmetric noise generation to simulate real-world noisy fundus image datasets. Experimental results demonstrate that our proposed method outperforms existing approaches in handling label noise, showing superior performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18147 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss Ye, Mengwen Huangfu, Yingzi Li, You Yu, Zekuan Computer Vision and Pattern Recognition Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-Supervised Pre-training with Robust Adaptive Credal Loss (SSP-RACL), for handling label noise in fundus image datasets. First, we use Masked Autoencoders (MAE) for pre-training to extract features, unaffected by label noise. Subsequently, RACL employ a superset learning framework, setting confidence thresholds and adaptive label relaxation parameter to construct possibility distributions and provide more reliable ground-truth estimates, thus effectively suppressing the memorization effect. Additionally, we introduce clinical knowledge-based asymmetric noise generation to simulate real-world noisy fundus image datasets. Experimental results demonstrate that our proposed method outperforms existing approaches in handling label noise, showing superior performance. |
| title | SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.18147 |