Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval
This work addresses the challenge of retrieving images from unseen sketch queries in computer vision, offering a more efficient approach by eliminating the need for aligned pairs, though it is incremental as it builds on existing generative and adversarial methods.
The authors tackled the problem of zero-shot sketch-based image retrieval by proposing a semantically aligned paired cycle-consistent generative model that maps visual information to a common semantic space without requiring aligned sketch-image pairs, achieving a significant boost in performance over state-of-the-art methods on Sketchy and TU-Berlin datasets.
Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains a cycle consistency that only requires supervision at category levels, and avoids the need of highly-priced aligned sketch-image pairs. A classification criteria on the generators' outputs ensures the visual to semantic space mapping to be discriminating. Furthermore, we propose to combine textual and hierarchical side information via a feature selection auto-encoder that selects discriminating side information within a same end-to-end model. Our results demonstrate a significant boost in zero-shot SBIR performance over the state-of-the-art on the challenging Sketchy and TU-Berlin datasets.