TY - CONF AU - Anjan Dutta AU - Zeynep Akata A2 - CVPR PY - 2019// TI - Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval BT - 32nd IEEE Conference on Computer Vision and Pattern Recognition SP - 5089 EP - 5098 N2 - 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. UR - https://ieeexplore.ieee.org/document/8954217 L1 - http://refbase.cvc.uab.es/files/DuA2019.pdf UR - http://dx.doi.org/10.1109/CVPR.2019.00523 N1 - DAG; 600.141; 600.121 ID - Anjan Dutta2019 ER -