Metraipolis › archive › dc_5446c686a905
Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning — arXiv:2609.01136
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01136
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:48.656Z
- SHA-256 of the archived text
f44718d79a4e9d1e1786dbe28f2f9ce0ec4c3c4380c132e9d51c29488dca1146- Stable URL of this page
https://metraipolis.com/documento/dc_5446c686a905
How to cite
Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning — arXiv:2609.01136 — arXiv (en), https://arxiv.org/abs/2609.01136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5446c686a905 (Metraipolis archive dc_5446c686a905, sha256 f44718d79a4e9d1e1786dbe28f2f9ce0ec4c3c4380c132e9d51c29488dca1146)
BibTeX
@misc{dc5446c686a905,
title = {Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning — arXiv:2609.01136},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01136},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5446c686a905; sha256 f44718d79a4e9d1e1786dbe28f2f9ce0ec4c3c4380c132e9d51c29488dca1146},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Change captioning is the task of generating natural language descriptions that explain the changes between a pair of images. Although different change types (e.g., color shifts, object additions) exhibit distinct visual cues and require specialized reasoning processes, existing methods often overlook these distinctions. To address this limitation, we propose Multi-Expert Diagnosis for Image Change (MEDIC), a novel framework that introduces change-type awareness by explicitly modeling change categories. MEDIC employs type-specialized memory experts that dynamically retrieve type-relevant visual patterns conditioned on the input. This design enables each expert to capture diverse variations within its change type while focusing on the most informative visual cues. By softly routing inputs across type-specialized experts and learning dedicated representations for each change category, MEDIC generates more precise and type-aware change descriptions. Extensive experiments demonstrate that the proposed MEDIC consistently outperforms existing methods across diverse and challenging datasets. The code is available at \href{ this https URL }{GitHub}.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.01136 — 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 2026-10-17T07:00:58.966Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).