ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914582999597056 |
|---|---|
| author | Imtiaz, Romil Iakovidis, Dimitris K. |
| author_facet | Imtiaz, Romil Iakovidis, Dimitris K. |
| contents | We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17784 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis Imtiaz, Romil Iakovidis, Dimitris K. Computer Vision and Pattern Recognition Machine Learning We developed a multi-label gastrointestinal video analysis pipeline based on a ResNet-50 frame classifier followed by anatomy-guided temporal event decoding. The system predicts 17 labels, including 5 anatomy classes and 12 pathology classes, from frames resized to 336x336. A major challenge was severe class imbalance, particularly for rare pathology labels. To address this, we used clipped class-wise positive weighting in the training loss, which improved rare-class learning while maintaining stable optimization. At the temporal stage, we found that direct frame-to-event conversion produced fragmented mismatches with the official ground truth. The final submission therefore combined GT-style framewise event composition, anatomy vote smoothing, and anatomy-based pathology gating with a conservative hysteresis decoder. This design improved the final temporal mAP from 0.3801 to 0.4303 on the challenge test set. |
| title | ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2603.17784 |