SOURCE-LINKED INTELLIGENCE

Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

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 co

Read original source ↗ Open in workspace

recordType

paper

region

Global