{"type":"ScholarlyArticle","title":"Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval","authors":[{"name":"Zhipeng Wang","slug":"zhipeng-wang","given":"Zhipeng","family":"Wang","affiliation":""},{"name":"Hao Wang","slug":"hao-wang","given":"Hao","family":"Wang","affiliation":""},{"name":"Jiexi Yan","slug":"jiexi-yan","given":"Jiexi","family":"Yan","affiliation":""},{"name":"Aming Wu","slug":"aming-wu","given":"Aming","family":"Wu","affiliation":""},{"name":"Cheng Deng","slug":"cheng-deng","given":"Cheng","family":"Deng","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/158","url":"https://ijcai.org/proceedings/2021/158","pdf":"https://ijcai.org/proceedings/2021/0158.pdf","markdown":"https://ijcai.org/proceedings/2021/158.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/158","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision II","track":"Main Track","number":158,"pages":{"first":1143,"last":1149},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}