Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914620046835712 |
|---|---|
| author | Pham, Ha-Hieu Nguyen, Hai-Dang Nguyen, Thanh-Huy Xu, Min Bagci, Ulas Le, Trung-Nghia Pham, Huy-Hieu |
| author_facet | Pham, Ha-Hieu Nguyen, Hai-Dang Nguyen, Thanh-Huy Xu, Min Bagci, Ulas Le, Trung-Nghia Pham, Huy-Hieu |
| contents | Chest X-Ray (CXR) classification in clinical practice is often limited by imperfect supervision, arising from (i) extreme long-tailed multi-label disease distributions and (ii) missing annotations for rare or previously unseen findings. The CXR-LT 2026 challenge addresses these issues on a PadChest-based benchmark with a 36-class label space split into 30 in-distribution classes for training and 6 out-of-distribution (OOD) classes for zero-shot evaluation. We present task-specific solutions tailored to the distinct supervision regimes. For Task 1 (long-tailed multi-label classification), we adopt an imbalance-aware multi-label learning strategy to improve recognition of tail classes while maintaining stable performance on frequent findings. For Task 2 (zero-shot OOD recognition), we propose a prediction approach that produces scores for unseen disease categories without using any supervised labels or examples from the OOD classes during training. Evaluated with macro-averaged mean Average Precision (mAP), our method achieves strong performance on both tasks, ranking first on the public leaderboard of the development phase. Code and pre-trained models are available at https://github.com/hieuphamha19/CXR_LT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13430 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning Pham, Ha-Hieu Nguyen, Hai-Dang Nguyen, Thanh-Huy Xu, Min Bagci, Ulas Le, Trung-Nghia Pham, Huy-Hieu Computer Vision and Pattern Recognition Chest X-Ray (CXR) classification in clinical practice is often limited by imperfect supervision, arising from (i) extreme long-tailed multi-label disease distributions and (ii) missing annotations for rare or previously unseen findings. The CXR-LT 2026 challenge addresses these issues on a PadChest-based benchmark with a 36-class label space split into 30 in-distribution classes for training and 6 out-of-distribution (OOD) classes for zero-shot evaluation. We present task-specific solutions tailored to the distinct supervision regimes. For Task 1 (long-tailed multi-label classification), we adopt an imbalance-aware multi-label learning strategy to improve recognition of tail classes while maintaining stable performance on frequent findings. For Task 2 (zero-shot OOD recognition), we propose a prediction approach that produces scores for unseen disease categories without using any supervised labels or examples from the OOD classes during training. Evaluated with macro-averaged mean Average Precision (mAP), our method achieves strong performance on both tasks, ranking first on the public leaderboard of the development phase. Code and pre-trained models are available at https://github.com/hieuphamha19/CXR_LT. |
| title | Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.13430 |