SOURCE-LINKED INTELLIGENCE

FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Fine-grained visual understanding depends on local detail, yet visual encoders face a trade-off between costly full-image high-resolution processing and compact global encoding that can weaken such evidence. Inspired by human active vision, we separate where to look from what to encode. We focus on the latter and introduce FAVE (Foveated Adaptive Visual Encoding), a lightweight variable-resolution ViT that encodes externally selected regions at high acuity while preserving native geometry. We first isolate this encoding problem using oracle ground-truth crops in a controlled small-object regim

Read original source ↗ Open in workspace

recordType

paper

region

Global