region-based representations

1 paper across 1 session

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders

#4614 · Savya Khosla, Sethuraman T V, Barnett Lee, Alex Schwing, Derek Hoiem

REN extracts object-centric region tokens from frozen vision features using point prompts—no segmentation needed. It’s 60× faster and 35× lighter than SAM, with strong performance across tasks.