SOURCE-LINKED INTELLIGENCE

Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception

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

State-of-the-art vision models process images in their entirety, lacking the ability to selectively zoom in on relevant regions. This limitation is particularly acute in scenarios where processing must be conditioned on a specific task - such as instance detection, which requires localizing a specific object in a high-resolution, cluttered scene. In such settings, critical details are easily lost as images are often resized to match the model dimensions and computational constraints. We introduce Coarse-to-Fine Glimpse-based Active Perception (CF-GAP), a task-driven front-end that enhances hig

Read original source ↗ Open in workspace

recordType

paper

region

Global