MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders
Text-to-image retrieval with frozen dual encoders degrades when the query names a small, visually subordinate object in a cluttered scene: a single global image embedding underrepresents the localized visual evidence. We present MINER, a training-free inference framework that augments a frozen dual encoder's global image embedding with a small bank of region-level embeddings and a hubness-correcting similarity rescoring, recovering visual evidence that global pooling underweights. To evaluate this setting, we introduce ROCS, a benchmark built from high-clutter subsets of Flickr30K and MS COCO whose images are re-captioned to name a single low-salience object. Experiments on CLIP, SigLIP, ...
| Authors | Abdulmalik Alquwayfili, Faisal AlMeshal, Jumanah Almajnouni et al. |
|---|---|
| Primary category | cs.CV |
| Published | 22 September 2026 |
| Last updated at source | 22 September 2026 |
Models and datasets referencing this paper
- aalquwayfili/ROCSDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.