-
[pdf]
[supp]
[bibtex]@InProceedings{Lyou_2024_WACV, author = {Lyou, Eunyi and Lee, Doyeon and Kim, Jooeun and Lee, Joonseok}, title = {Modality-Aware Representation Learning for Zero-Shot Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5646-5655} }
Modality-Aware Representation Learning for Zero-Shot Sketch-Based Image Retrieval
Abstract
Zero-shot learning offers an efficient solution for a machine learning model to treat unseen categories, avoiding exhaustive data collection. Zero-shot Sketch-based Image Retrieval (ZS-SBIR) simulates real-world scenarios where it is hard and costly to collect paired sketch-photo samples. We propose a novel framework that indirectly aligns sketches and photos by contrasting them through texts, removing the necessity of access to sketch-photo pairs. With an explicit modality encoding learned from data, our approach disentangles modality-agnostic semantics from modality-specific information, bridging the modality gap and enabling effective cross-modal content retrieval within a joint latent space. From comprehensive experiments, we verify the efficacy of the proposed model on ZS-SBIR, and it can be also applied to generalized and fine-grained settings.
Related Material