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

arXiv:2609.09025v1 Announce Type: new Abstract: 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 high-resolution processing of existing instance detectors. CF-GAP selectively directs a sequence of limited view glimpses across the scene, utilizing task information to iteratively refine focus on the most relevant regions. These localized regions are then processed at high resolution by a downstream instance detector. By avoiding full-image processing and eliminating irrelevant confounding information, CF-GAP improves Average Precision (AP) by up to 20% across various state-of-the-art instance detectors on the HR-InsDet and Robotools benchmarks, while further enabling lightweight detectors to outperform their larger counterparts.

Related

• GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding
• CanViT: Toward Active-Vision Foundation Models
• Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG
• ActiveScope: Actively Seeking and Correcting Perception for MLLMs

Source: arXiv cs.CV | 2026-09-09