Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal
retrieval task, where abstract sketches are used as queries to retrieve natural
images under zero-shot scenario. Most existing methods regard ZS-SBIR as a
traditional classification problem and employ a cross-entropy or triplet-based
loss to achieve retrieval, which neglect the problems of the domain gap between
sketches and natural images and the large intra-class diversity in sketches.
Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR.
Specifically, a cross-modal contrastive method is proposed to learn generalized
representations to smooth the domain gap by mining relations with additional
augmented samples. Furthermore, a category-specific memory bank with sketch
features is explored to reduce intra-class diversity in the sketch domain.
Extensive experiments demonstrate that our approach notably outperforms the
state-of-the-art methods in both Sketchy and TU-Berlin datasets. Our source
code is publicly available at this https URL

该研究提出了一种基于领域平滑网络 (DSN) 的零样本图形检索 (ZS-SBIR) 方法，该方法通过使用跨模态对比方法挖掘增强样本的关系以平滑领域差距，并在草图领域中探索类别特定的记忆库来减少草图的内类别差异。实验结果表明，该方法在 Sketchy 和 TU-Berlin 数据集中表现出色。