论文标题
UIGR：统一的互动服装检索
UIGR: Unified Interactive Garment Retrieval
论文作者
论文摘要
交互式服装检索（IGR）旨在根据参考服装图像检索目标服装图像，以及用户对参考服装上的更改的反馈。已经对两个IGR任务进行了广泛的研究：文本引导的服装检索（TGR）和视觉兼容的服装检索（VCR）。前者的用户反馈指示了保留服装类别要更改的语义属性，而该类别是后者唯一要明确更改的东西，对样式保存的隐含要求。尽管这两个任务与对有效系统的实际需求之间的相似性，但它们从未被统一和建模。在本文中，我们提出了一个统一的互动服装检索（UIGR）框架来统一TGR和VCR。为此，我们首先为这两个问题提供了一个大规模的基准。我们进一步提出了一个强大的基线体系结构，以将TGR和VCR集成到一个模型中。广泛的实验表明，在一个框架中统一两个任务不仅通过仅需要单个模型来提高效率，还会导致更好的性能。代码和数据集可在https://github.com/brandonhanx/compfashion上找到。
Interactive garment retrieval (IGR) aims to retrieve a target garment image based on a reference garment image along with user feedback on what to change on the reference garment. Two IGR tasks have been studied extensively: text-guided garment retrieval (TGR) and visually compatible garment retrieval (VCR). The user feedback for the former indicates what semantic attributes to change with the garment category preserved, while the category is the only thing to be changed explicitly for the latter, with an implicit requirement on style preservation. Despite the similarity between these two tasks and the practical need for an efficient system tackling both, they have never been unified and modeled jointly. In this paper, we propose a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR. To this end, we first contribute a large-scale benchmark suited for both problems. We further propose a strong baseline architecture to integrate TGR and VCR in one model. Extensive experiments suggest that unifying two tasks in one framework is not only more efficient by requiring a single model only, it also leads to better performance. Code and datasets are available at https://github.com/BrandonHanx/CompFashion.
