Metraipolis › archive › dc_33f5cd069f65
Adaptive Observation Control for Active Visual Recognition — arXiv:2610.19624
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19624
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:56:19.539Z
- SHA-256 of the archived text
1c186f6d484f868927d8338de9d03da741ccf72ee11853d6bbab5f8ea1f86f54- Stable URL of this page
https://metraipolis.com/documento/dc_33f5cd069f65
How to cite
Adaptive Observation Control for Active Visual Recognition — arXiv:2610.19624 — arXiv (en), https://arxiv.org/abs/2610.19624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33f5cd069f65 (Metraipolis archive dc_33f5cd069f65, sha256 1c186f6d484f868927d8338de9d03da741ccf72ee11853d6bbab5f8ea1f86f54)
BibTeX
@misc{dc33f5cd069f65,
title = {Adaptive Observation Control for Active Visual Recognition — arXiv:2610.19624},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19624},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33f5cd069f65; sha256 1c186f6d484f868927d8338de9d03da741ccf72ee11853d6bbab5f8ea1f86f54},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual recognition models usually process a fixed view under a fixed computation budget, although images often benefit from different scales and amounts of spatial evidence. Active vision can adapt by observing a coarse scene and then selecting informative fixations, but the public AdaptiveNN-DeiT-S pipeline still fixes both field of view and observation count. We extend this fixed-step recognizer with a controllable observation interface that adapts both the field of view and the number of fixations to the input. Specifically, the model predicts a per-fixation scale that sets its field of view, refines each selected crop with optional scale-gated foveation and a residual high-resolution detail-token branch, and uses label-grounded stop heads for input-dependent early termination. Experiments across fine-grained benchmarks, full ImageNet-1K, and ImageNet-A/R-derived classification splits show that the interface remains competitive with fixed-step references while exposing a controllable observation budget. The same checkpoint enables threshold-controlled accuracy-compute trade-offs without per-threshold retraining. On sequential ImageNet-1K, the learned stop rule outperforms fixed-step truncation of the same checkpoint, sustaining 81.9% top-1 using 2.45 of the four focus steps and exceeding three-step truncation at lower cost. On each benchmark, a variant combining scale control and detail-token fusion achieves the highest accuracy among the tested component-added non-exit variants. Our code is available at this https URL . 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/2610.19624 — 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 2026-10-15T21:38:29.482Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).