Metraipolis › archive › dc_8b26ff43db65
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception — arXiv:2609.37123
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37123
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:40:57.922Z
- SHA-256 of the archived text
d228cabbdc04ada9f6ca5c2f53cc52d8689a3ccad5a4ab107c05694c4715c52f- Stable URL of this page
https://metraipolis.com/documento/dc_8b26ff43db65
How to cite
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception — arXiv:2609.37123 — arXiv (en), https://arxiv.org/abs/2609.37123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b26ff43db65 (Metraipolis archive dc_8b26ff43db65, sha256 d228cabbdc04ada9f6ca5c2f53cc52d8689a3ccad5a4ab107c05694c4715c52f)
BibTeX
@misc{dc8b26ff43db65,
title = {EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception — arXiv:2609.37123},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37123},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b26ff43db65; sha256 d228cabbdc04ada9f6ca5c2f53cc52d8689a3ccad5a4ab107c05694c4715c52f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fine-grained visual perception enables vision-language models to distinguish subtle attributes and ground their answers in visual evidence. In high-resolution scenes, processing the whole image at greater resolution spends visual tokens on irrelevant content, while isolated crops can lose the context needed to interpret the selected evidence. We introduce EviViT, a lightweight attachment that learns where a pretrained vision transformer should acquire detail. Human visual-search traces supervise a question-conditioned evidence density, which guides regional re-reading from the original pixels and the allocation of visual tokens. A sparse, coordinate-aware bridge then connects the regional features to the global scene, allowing the host to interpret precise evidence in context. Learned with the host backbone frozen, the attachment serves both the base model and compatible post-trained descendants without refitting. Experiments across nine hosts show consistent gains in average fine-grained accuracy. Matched-budget comparisons further show that EviViT outperforms global-only processing at every tested token ceiling while using fewer visual tokens. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.37123 — 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 2026-10-07T18:04:24.824Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).