Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2503.17034 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910888430141440 |
|---|---|
| author | Lloyd-Brown, Stephen Francis, Susan Hoad, Caroline Gowland, Penny Mullinger, Karen French, Andrew Chen, Xin |
| author_facet | Lloyd-Brown, Stephen Francis, Susan Hoad, Caroline Gowland, Penny Mullinger, Karen French, Andrew Chen, Xin |
| contents | An often overlooked problem in medical image segmentation research is the effective selection of training subsets to annotate from a complete set of unlabelled data. Many studies select their training sets at random, which may lead to suboptimal model performance, especially in the minimal supervision setting where each training image has a profound effect on performance outcomes. This work aims to address this issue. We use prototypical contrasting learning and clustering to extract representative and diverse samples for annotation. We improve upon prior works with a bespoke cluster-based image selection process. Additionally, we introduce the concept of unsupervised balanced batch dataloading to medical image segmentation, which aims to improve model learning with minimally annotated data. We evaluated our method on a public skin lesion dataset (ISIC 2018) and compared it to another state-of-the-art data sampling method. Our method achieved superior performance in a low annotation budget scenario. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17034 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Attentive Representative Sample Selection Strategy Combined with Balanced Batch Training for Skin Lesion Segmentation Lloyd-Brown, Stephen Francis, Susan Hoad, Caroline Gowland, Penny Mullinger, Karen French, Andrew Chen, Xin Computer Vision and Pattern Recognition Artificial Intelligence An often overlooked problem in medical image segmentation research is the effective selection of training subsets to annotate from a complete set of unlabelled data. Many studies select their training sets at random, which may lead to suboptimal model performance, especially in the minimal supervision setting where each training image has a profound effect on performance outcomes. This work aims to address this issue. We use prototypical contrasting learning and clustering to extract representative and diverse samples for annotation. We improve upon prior works with a bespoke cluster-based image selection process. Additionally, we introduce the concept of unsupervised balanced batch dataloading to medical image segmentation, which aims to improve model learning with minimally annotated data. We evaluated our method on a public skin lesion dataset (ISIC 2018) and compared it to another state-of-the-art data sampling method. Our method achieved superior performance in a low annotation budget scenario. |
| title | An Attentive Representative Sample Selection Strategy Combined with Balanced Batch Training for Skin Lesion Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.17034 |