We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
WAD-CMSN: Wasserstein distance-based cross-modal semantic network for zero-shot sketch-based image retrieval.
- Authors
Xu, Guanglong; Hu, Zhensheng; Cai, Jia
- Abstract
Zero-shot sketch-based image retrieval (ZSSBIR) aims at retrieving natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low-dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance-based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low-dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, a novel identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors.
- Subjects
TECHNISCHE Universitat Berlin; IMAGE retrieval; DEPERSONALIZATION
- Publication
International Journal of Wavelets, Multiresolution & Information Processing, 2023, Vol 21, Issue 2, p1
- ISSN
0219-6913
- Publication type
Article
- DOI
10.1142/S0219691322500540