Metraipolis › archive › dc_1910ab18b0cd
STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models — arXiv:2608.05808
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05808
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:16.984Z
- SHA-256 of the archived text
4642dc1eae9f23b88a30a70d5949358b7084694c22d1595ca02548ec01f39e54- Stable URL of this page
https://metraipolis.com/documento/dc_1910ab18b0cd
How to cite
STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models — arXiv:2608.05808 — arXiv (en), https://arxiv.org/abs/2608.05808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1910ab18b0cd (Metraipolis archive dc_1910ab18b0cd, sha256 4642dc1eae9f23b88a30a70d5949358b7084694c22d1595ca02548ec01f39e54)
BibTeX
@misc{dc1910ab18b0cd,
title = {STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models — arXiv:2608.05808},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05808},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1910ab18b0cd; sha256 4642dc1eae9f23b88a30a70d5949358b7084694c22d1595ca02548ec01f39e54},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning models applied to medical image analysis suffer from severe catastrophic forgetting when continually adapting to new clinical tasks in dynamic environments. Mainstream incremental learning methods typically mitigate this by rehearsing raw historical images. However, this pixel-level rehearsal incurs significant storage overhead, raises privacy concerns, and fails to adequately capture the true data distribution with sparse exemplars. Inspired by human cognitive mechanisms, we propose a novel framework termed Semantic Text-Anchored Incremental Learning (STAIL) for sequential clinical tasks. To overcome the rehearsal bottleneck, STAIL introduces an asymmetric semantic consolidation buffer (SCB). By incorporating a minimal set of image anchors and extensive textual descriptions, the SCB enables dense semantic reconstruction of old tasks at a minimal storage cost. Furthermore, we design an LLM-derived Semantic Anchoring Mechanism (LSAM) that leverages the stable semantic space of frozen large language models as developmental priors. This mechanism explicitly anchors evolving visual features to textual representations, guiding and constraining plasticity and stability at both macroscopic and microscopic levels. Extensive experiments across three heterogeneous medical datasets, covering fundus, ultrasound, and X-ray imaging, demonstrate that STAIL acts as a highly effective plug-and-play module. It comprehensively enhances the performance of various existing baselines, achieving average gains of 2.24\% in AAA-AUC for sustained performance and 3.55\% in BWT-AUC for reduced forgetting. Code is available. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05808 — 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 2026-10-31T10:23:31.021Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).