Back to Search
Start Over
Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
- Source :
- IJCAI
- Publication Year :
- 2021
- Publisher :
- International Joint Conferences on Artificial Intelligence Organization, 2021.
-
Abstract
- 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.<br />Comment: Accepted to IJCAI 2021
- Subjects :
- FOS: Computer and information sciences
Source code
Information retrieval
Computer science
Computer Vision and Pattern Recognition (cs.CV)
media_common.quotation_subject
Computer Science - Computer Vision and Pattern Recognition
Sketch
Task (project management)
Domain (software engineering)
Zero (linguistics)
Memory bank
Image retrieval
Smoothing
media_common
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
- Accession number :
- edsair.doi.dedup.....71ad73c96d10af4991571e2ed646d997