Metraipolis › archive › dc_228efcf569fb
Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies — arXiv:2609.08408
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08408
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:20.060Z
- SHA-256 of the archived text
3fa88dc4ed084dd9dd08465fda0adbf3106c3d4532a074a0b8bb5cb1388aa1a1- Stable URL of this page
https://metraipolis.com/documento/dc_228efcf569fb
How to cite
Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies — arXiv:2609.08408 — arXiv (en), https://arxiv.org/abs/2609.08408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_228efcf569fb (Metraipolis archive dc_228efcf569fb, sha256 3fa88dc4ed084dd9dd08465fda0adbf3106c3d4532a074a0b8bb5cb1388aa1a1)
BibTeX
@misc{dc228efcf569fb,
title = {Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies — arXiv:2609.08408},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08408},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_228efcf569fb; sha256 3fa88dc4ed084dd9dd08465fda0adbf3106c3d4532a074a0b8bb5cb1388aa1a1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Focusing on spatially localized, control-relevant visual cues has been shown to improve data efficiency in visuomotor policies by reducing the need to model task-irrelevant visual variation. Existing methods often impose this focus through input preprocessing, such as cropping control- or object-centric regions in RGB images or point-clouds. However, it remains underexplored whether such localized features can be exposed directly from commonly used convolutional neural network (CNN) encoded features. In this paper, we show that intermediate CNN features preserve localized visual context for control, but existing pooling methods fail to aggregate it effectively. We introduce FocusPool, an attention pooling module that selectively aggregates intermediate visual features according to their relevance to the robot's current proprioceptive context. The resulting pooled representation captures task-progressive, control-relevant local information and is used directly for policy learning. Across simulation and real-world experiments, FocusPool improves policy success rates over pooling and explicit local focus methods by 36.2% and 41.2%, with training only 5.8% of encoder parameters. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.08408 — 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 2026-10-16T15:11:47.631Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).