Cross-domain retrieval (CDR), as a crucial tool for numerous technologies, is
finding increasingly broad applications. However, existing efforts face several
major issues, with the most critical being the need for accurate supervision,
which often demands costly resources and efforts. Cutting-edge studies focus on
achieving unsupervised CDR but typically assume that the category spaces across
domains are identical, an assumption that is often unrealistic in real-world
scenarios. This is because only through dedicated and comprehensive analysis
can the category spaces of different domains be confirmed as identical, which
contradicts the premise of unsupervised scenarios. Therefore, in this work, we
introduce the problem of Universal Unsupervised Cross-Domain Retrieval (U^2CDR)
for the first time and design a two-stage semantic feature learning framework
to address it. In the first stage, a cross-domain unified prototypical
structure is established under the guidance of an instance-prototype-mixed
contrastive loss and a semantic-enhanced loss, to counteract category space
differences. In the second stage, through a modified adversarial training
mechanism, we ensure minimal changes for the established prototypical structure
during domain alignment, enabling more accurate nearest-neighbor searching.
Extensive experiments across multiple datasets and scenarios, including closet,
partial, and open-set CDR, demonstrate that our approach significantly
outperforms existing state-of-the-art CDR works and some potentially effective
studies from other topics in solving U^2CDR challenges.

本文首次引入了 “通用无监督跨领域检索（U^2CDR）” 问题，并设计了一个两阶段的语义特征学习框架来解决该问题。在第一阶段，通过实例 - 原型 - 混合对比损失和语义增强损失，在域间保持一个跨领域统一的原型结构以应对类别空间差异。在第二阶段，通过修改的对抗训练机制，在领域对齐过程中保持已建立的原型结构的最小变化，从而实现更准确的最近邻搜索。对多个数据集和场景进行了广泛实验，包括闭集、部分集和开集 CDR，结果表明我们的方法在解决 U^2CDR 挑战方面显著优于现有最先进的 CDR 方法以及其他主题中一些潜在有效的研究。