cs.AINov 17, 2026

LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model

Authors: Rahim Hossain, Dipanwita Saha, Ashirbad Mishra, Xinxin Shu, Svetlana Strunjas, Binbin Li

Organizations: Binghamton University · eBay Inc.

Abstract

Whole image embeddings can under represent small objects and local attributes that distinguish relevant images for localized queries. We present LoCaR, a training free framework for localized text to image retrieval with frozen vision language models. LoCaR constructs and utilizes independent proposals (SAM2) focusing on the object so as to get a more localized representation that independently encodes each region using the frozen visual encoder. We further study paired-support adaptation as an optional residual that uses matched text region exemplars without updating the underlying encoders. We also introduce LOCFG, a Visual Genome derived benchmark designed to evaluate localized retrieval for smaller and more challenging referents. Across several vision language backbones, our results show that improving the region representation itself is the main source of gain.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LOCI: A Locator-Critic with Refinement Loop

    Aug 31, 2026Walid Bousselham, Mathilde Caron, Arsha Nagrani +1Visual Question AnsweringVision-Language Grounding

  2. MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders

    Sep 22, 2026Abdulmalik Alquwayfili, Faisal AlMeshal, Jumanah Almajnouni +2Vision-Language RetrievalImage Retrieval