Metraipolis › archive › dc_35aea5ecbcb6
Task-Performance Routing for Multi-Teacher Distillation in CT Medical Image Segmentation — arXiv:2610.41362
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41362
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T08:02:48.839Z
- SHA-256 of the archived text
744d414c10c218da9c70992b36ce5a961c9a93d9594b3c4a64b818022668f949- Stable URL of this page
https://metraipolis.com/documento/dc_35aea5ecbcb6
How to cite
Task-Performance Routing for Multi-Teacher Distillation in CT Medical Image Segmentation — arXiv:2610.41362 — arXiv (en), https://arxiv.org/abs/2610.41362 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35aea5ecbcb6 (Metraipolis archive dc_35aea5ecbcb6, sha256 744d414c10c218da9c70992b36ce5a961c9a93d9594b3c4a64b818022668f949)
BibTeX
@misc{dc35aea5ecbcb6,
title = {Task-Performance Routing for Multi-Teacher Distillation in CT Medical Image Segmentation — arXiv:2610.41362},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41362},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35aea5ecbcb6; sha256 744d414c10c218da9c70992b36ce5a961c9a93d9594b3c4a64b818022668f949},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41362. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pre-trained models offer complementary strengths in CT organ segmentation, but their relative accuracy varies across organs and spatial regions. Multi-teacher knowledge distillation can combine these strengths in a single student, yet global or instance-level teacher weights overlook variation within a 3D volume. We propose Task-Performance Routing (TPR), which uses region-wise segmentation errors to determine teacher weights during training without learned routing parameters. In hard regions, TPR favors teachers with lower prediction errors; in easy regions, it uses uniform weights to combine their knowledge. A hierarchical spatial partition provides fine-grained routing in shallow encoder stages and coarse-grained routing in deep stages. Experiments on BTCV, MSD-Liver, and MSD-Pancreas with two teacher pairs and two backbone architectures show higher Dice scores than the individual teachers, adaptive ensembles, and evaluated multi-teacher distillation baselines. On MSD-Pancreas, TPR achieves Dice scores of 65.40% with SwinUNETR and 68.25% with U-Net, compared with 64.38% and 67.45% for the corresponding adaptive ensembles. Inference uses the student alone, with no routing or teacher overhead. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.41362 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-02T07:44:00.747Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).