Towards Unsupervised Sketch-based Image Retrieval
Conghui Hu (National University of Singapore),* Yongxin Yang (University of Surrey), Yunpeng Li (University of Surrey), Timothy Hospedales (Edinburgh University), Yi-Zhe Song (University of Surrey)
The 33rd British Machine Vision Conference
Abstract
The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling. In this paper, we present the first attempt at unsupervised SBIR to remove the labeling cost (both category annotations and sketch-photo pairings) that is conventionally needed for training. Existing single-domain unsupervised representation learning methods perform poorly in this application, due to the unique cross-domain (sketch and photo) nature of the problem. We therefore introduce a novel framework that simultaneously performs sketch-photo domain alignment and semantic-aware representation learning. Technically this is underpinned by introducing joint distribution optimal transport (JDOT) to align data from different domains, which we extend with trainable cluster prototypes and feature memory banks to further improve scalability and efficacy. Extensive experiments show that our framework achieves excellent performance in the new unsupervised setting, and performs comparably to existing zero-shot SBIR methods.Video
Citation
@inproceedings{Hu_2022_BMVC,
author = {Conghui Hu and Yongxin Yang and Yunpeng Li and Timothy Hospedales and Yi-Zhe Song},
title = {Towards Unsupervised Sketch-based Image Retrieval},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0224.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by