Metraipolis › archive › dc_09ce41c4f030
GroundSeek-CXR: Retrospective Evaluation-Guided Active Observation Framework for Multi-Label Chest Radiography Diagnosis — arXiv:2611.04286
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04286
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:56:17.470Z
- SHA-256 of the archived text
dbdcdd50acb24fe4b2e63c7977e1783289127e98f0c7c40dc4d229ef3d542e3a- Stable URL of this page
https://metraipolis.com/documento/dc_09ce41c4f030
How to cite
GroundSeek-CXR: Retrospective Evaluation-Guided Active Observation Framework for Multi-Label Chest Radiography Diagnosis — arXiv:2611.04286 — arXiv (en), https://arxiv.org/abs/2611.04286 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09ce41c4f030 (Metraipolis archive dc_09ce41c4f030, sha256 dbdcdd50acb24fe4b2e63c7977e1783289127e98f0c7c40dc4d229ef3d542e3a)
BibTeX
@misc{dc09ce41c4f030,
title = {GroundSeek-CXR: Retrospective Evaluation-Guided Active Observation Framework for Multi-Label Chest Radiography Diagnosis — arXiv:2611.04286},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04286},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09ce41c4f030; sha256 dbdcdd50acb24fe4b2e63c7977e1783289127e98f0c7c40dc4d229ef3d542e3a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04286. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Chest radiography (CXR) diagnosis is critical for thoracic disease assessment, yet challenged by the need to identify subtle lesions and co-occurring abnormalities across regions. While recent vision-language models can actively observe local regions, existing preference-based methods supervise each observation by its immediate effect on the current diagnosis, failing to capture how each observation and stopping decision contributes to the final diagnosis. To address this issue, we propose GroundSeek-CXR, an active CXR diagnosis framework that learns observation and stopping decisions by retrospectively evaluating them with the final diagnosis. Specifically, we first devise a Retrospective Diagnostic Evaluation (RDE) that scores observation and stop candidates from offline Monte Carlo tree search through independent continuations. Moreover, we design a Retrospective Gap-weighted Preference Optimization (RGPO) that learns from retrospective-score preferences weighted by their score gaps, prioritizing actions that improve diagnostic accuracy. Extensive experiments demonstrate that our GroundSeek-CXR framework outperforms state-of-the-art methods, and improves abnormal-image sample-F1 by 4.48% over immediate-score preference learning. 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/2611.04286 — 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 2026-11-04T12:33:47.123Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).