We suggest a novel method and new benchmark for image retrieval with small objects

Hypernetwork-based framework for dynamic adaption of precomputed database features.

We distill a slow, unlearning-based data attribution method to a feature embedding space for efficient retrieval of highly influential training images.

We propose a VLM-assisted dual-space adaptation framework to improve unsupervised domain adaptive hashing by calibrating pseudo-labels and decoupling feature and Hamming space alignment.

We introduce i-CIR—an instance‐level composed image retrieval benchmark with rigorously curated hard negatives—and BASIC, a training‐free VLM‐based method that centers and projects image embeddings.