用局部描述符构建跨域图像相似性，高效且可解释。
ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
- 在相似性空间中操作，利用局部对应关系提升跨域适应力。
- 通过最优传输筛选有效描述符，投票聚合强对应关系，提升检索精度。
- 适合需要低计算成本的跨域图像检索场景，尤其适用于新领域部署。
大规模实例级训练数据稀缺，模型通常在特定领域数据上训练，但实际检索需应对多样化的数据域，因此对未见数据的泛化能力至关重要。本文提出ELViS，一种能在未见领域间有效泛化的图像到图像相似性模型。与传统方法不同，它在相似性空间而非表示空间中操作，促进跨域迁移。该模型利用局部描述符的对应关系，通过依赖数据的最优传输步骤抑制无信息描述符，并以投票机制聚合强对应关系，形成图像级相似性。这一设计引入强归纳偏置，使模型简单、高效且可解释。为评估泛化能力，我们构建了一个包含8个数据集的基准，涵盖地标、艺术品、产品及多领域集合，评估了ELViS作为重排序方法的表现。实验表明，在跨域场景和平均表现上，ELViS显著优于现有方法，且计算开销仅为它们的一小部分。代码已开源。
原文摘要 · Abstract (English)
Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, making generalization to unseen data critical. We introduce ELViS, an image-to-image similarity model that generalizes effectively to unseen domains. Unlike conventional approaches, our model operates in similarity space rather than representation space, promoting cross-domain transfer. It leverages local descriptor correspondences, refines their similarities through an optimal transport step with data-dependent gains that suppress uninformative descriptors, and aggregates strong correspondences via a voting process into an image-level similarity. This design injects strong inductive biases, yielding a simple, efficient, and interpretable model. To assess generalization, we compile a benchmark of eight datasets spanning landmarks, artworks, products, and multi-domain collections, and evaluate ELViS as a re-ranking method. Our experiments show that ELViS outperforms competing methods by a large margin in out-of-domain scenarios and on average, while requiring only a fraction of their computational cost. Code available at: https://github.com/pavelsuma/ELViS/
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。