Metraipolis › archive › dc_aa681f22dd73
SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis — arXiv:2610.22094
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22094
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:38:55.296Z
- SHA-256 of the archived text
a80bc42502c25d00c8801c8ef4bcee4bca818c0ba8acac1ce5e9b641cde2694e- Stable URL of this page
https://metraipolis.com/documento/dc_aa681f22dd73
How to cite
SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis — arXiv:2610.22094 — arXiv (en), https://arxiv.org/abs/2610.22094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa681f22dd73 (Metraipolis archive dc_aa681f22dd73, sha256 a80bc42502c25d00c8801c8ef4bcee4bca818c0ba8acac1ce5e9b641cde2694e)
BibTeX
@misc{dcaa681f22dd73,
title = {SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis — arXiv:2610.22094},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22094},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa681f22dd73; sha256 a80bc42502c25d00c8801c8ef4bcee4bca818c0ba8acac1ce5e9b641cde2694e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch as a negative. In radiology, recurring findings across patients mean that instance mismatch need not imply semantic incompatibility, creating false-negative supervision that we term a semantic conflict. A training-trace audit shows that pair-observations selected by the online mask used during training are enriched for report-derived finding agreement, although this proxy analysis does not establish clinical equivalence. Fixed thresholds can become miscalibrated as similarity distributions evolve, while soft reweighting leaves residual repulsive gradients. We therefore propose Semantic-Conflict-Aware Contrastive Learning (SCCL), which tracks modality-specific similarity distributions with exponential-moving-average (EMA) statistics, derives adaptive thresholds, and hard-masks flagged candidates before softmax normalization. Inclusive (OR) and consensus (AND) rules define two SCCL teachers, whose bidirectional cross-modal rankings are consolidated through standard distillation into a single deployable student, SCCL-DT. Across five public chest X-ray benchmarks, SCCL-DT achieves a mean zero-shot AUC of $0.850$, compared with $0.837$ for the strongest evaluated baseline in our comparison. Code will be made publicly available soon. 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/2610.22094 — 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 2026-10-16T08:52:02.718Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).