让图像检索模型自动适应不同画风，提升跨风格匹配准确率。
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
- 用超网络动态生成注意力层的奇异值扰动，实现按查询风格自适应调整。
- 在多个跨风格数据集上超越现有方法，零样本检索准确率提升显著。
- 轻量设计适合实际应用，尤其适合处理草图、艺术图等非标准输入。
基于查询的图像检索（QBIR）需在多样且风格多变的查询（如草图、艺术作品或低分辨率预览）下找到相关图像。尽管大规模视觉-语言表征模型（如CLIP）具备出色的零样本检索性能，但在面对未见过的查询风格时仍会因分布偏移而表现下降。本文提出超网络驱动的风格自适应检索框架Hystar，通过超网络为注意力层生成奇异值扰动（ΔS），实现对每条查询的动态权重调整；同时在MLP层采用静态奇异值偏移，保障跨风格稳定性。为缓解风格间语义混淆，设计了基于最优传输加权的对比损失StyleNCE，强化困难的跨风格负样本。在多风格检索与跨风格分类基准上的大量实验表明，Hystar持续优于强基线，达到当前最优性能，同时参数高效且风格鲁棒性优异。
原文摘要 · Abstract (English)
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 ($ΔS$) 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。