Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
It improves cross-modal retrieval for sketch-based image search, but appears incremental as it builds on existing contrastive and memory bank techniques.
The paper tackles zero-shot sketch-based image retrieval by addressing the domain gap between sketches and natural images and large intra-class sketch diversity, proposing a Domain-Smoothing Network that outperforms state-of-the-art methods on Sketchy and TU-Berlin datasets.
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 https://github.com/haowang1992/DSN.