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

Yujia Cai, Boxuan Li, Chenghao Xu, Jiexi Yan

Keywords: Image Retrieval, Vision–Language Representation Models, Hypernetworks, Style Adaptation, Contrastive Learning

TL;DR: Hystar dynamically adapts model weights per query style and uses StyleNCE to enable efficient, stable, and robust multi-style image retrieval.

Abstract: 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. Hystar employs a hypernetwork to generate singular-value perturbations ($\Delta S$) for attention layers, enabling flexible per-input adaptation, while static singular-value offsets on MLP layers ensure cross-style stability. To better handle semantic confusions across styles, we design StyleNCE as part of Hystar, an optimal-transport-weighted contrastive loss that emphasizes hard cross-style negatives. Extensive experiments on multi-style retrieval and cross-style classification benchmarks demonstrate that Hystar consistently outperforms strong baselines, achieving state-of-the-art performance while being parameter-efficient and stable across styles.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 8924