Metraipolis › archive › dc_dda13f91e44d
FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System — arXiv:2610.41987
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41987
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:21:56.059Z
- SHA-256 of the archived text
3a1089de7c562ecb701f4433fff3b5b23d875ba2aab8e5e1c285105d171dd8b3- Stable URL of this page
https://metraipolis.com/documento/dc_dda13f91e44d
How to cite
FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System — arXiv:2610.41987 — arXiv (en), https://arxiv.org/abs/2610.41987 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dda13f91e44d (Metraipolis archive dc_dda13f91e44d, sha256 3a1089de7c562ecb701f4433fff3b5b23d875ba2aab8e5e1c285105d171dd8b3)
BibTeX
@misc{dcdda13f91e44d,
title = {FoAViS: Analyzing Learned Fixation Strategies in a Foveated Active Vision System — arXiv:2610.41987},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41987},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dda13f91e44d; sha256 3a1089de7c562ecb701f4433fff3b5b23d875ba2aab8e5e1c285105d171dd8b3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41987. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Human vision is foveated and active: resolution is highest at the fovea and falls off towards the periphery, and fixations are actively directed to locations of interest. Building a machine system that processes information in the same way lets us study gaze behavior in a controlled setting where the system's components and objectives are known. The emergence of gaze characteristics can therefore be examined systematically, which may in turn inform our understanding of biological vision. This requires a model that can sample like the fovea, handle various tasks from classification to dense prediction, and be trained concurrently with a fixation policy. In our study, we present such a system and study its capabilities and the fixation policies that emerge from it. Our system, FoAViS, samples visual input by adopting the established log-polar foveation and accumulates information in a 2D spatial memory. Due to its 2D structure, the same memory can be read out globally for classification or densely for semantic segmentation, without any architectural change. Fixations are drawn from a 2D map by a policy trained concurrently with the task. We find that learned fixation policies select more informative, task-specific locations than non-learned heuristics. These policies also shape the task representations in a beneficial way: for both classification and segmentation, models trained concurrently with a policy outperform models trained with random locations, even when the latter are provided with learned scanpaths. Moreover, these scanpaths exhibit similarities to human gaze behavior by capturing aspects of empirical scanpath characteristics. Our work marks an important step away from standard passive, single-pass architectures, towards biologically grounded models of vision. It opens a path for studying goal-directed gaze behavior and information representation in the visual system. 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/2610.41987 — 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 2026-11-03T08:06:38.852Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).