Towards Unsupervised Sketch-based Image Retrieval
This addresses the high labeling costs in sketch-based image retrieval for applications like visual search, though it is incremental as it builds on existing unsupervised methods.
The paper tackles the problem of sketch-based image retrieval without requiring labeled data, by introducing an unsupervised framework that aligns sketch and photo domains and learns semantic-aware representations, achieving performance comparable to or better than state-of-the-art in zero-shot settings.
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 or better than state-of-the-art in the zero-shot setting.