AI RESEARCH

Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation

arXiv CS.CV

ArXi:2605.10009v1 Announce Type: new Query-based image retrieval (QBIR) requires retrieving relevant images given diverse and often stylistically heterogeneous queries, such as sketches, artworks, or low-resolution previews. While large-scale vision--language representation models (VLRMs) like CLIP offer strong zero-shot retrieval performance, they struggle with distribution shifts caused by unseen query styles. In this paper, we propose the Hypernetwork-driven Style-adaptive Retrieval (Hystar), a lightweight framework that dynamically adapts model weights to each query's style.