2021/08/18 by Soumava Paul, Paul, Soumava, Titir Dutta +3
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.2108.08356
Accepted at ICCV 2021. 15 pages, 6 figures
arxiv created 2021/08/18 · openalex publication_date 2021/08/18 · arxiv updated 2021/08/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this work, for the first time, we address the problem of universal cross-domain retrieval, where the test data can belong to classes or domains which are unseen during training. Due to dynamically increasing number of categories and practical constraint of training on every possible domain, which requires large amounts of data, generalizing to both unseen classes and domains is important. Towards that goal, we propose SnMpNet (Semantic Neighbourhood and Mixture Prediction Network), which incorporates two novel losses to account for the unseen classes and domains encountered during testing. Specifically, we introduce a novel Semantic Neighborhood loss to bridge the knowledge gap between seen and unseen classes and ensure that the latent space embedding of the unseen classes is semantically meaningful with respect to its neighboring classes. We also introduce a mix-up based supervision at image-level as well as semantic-level of the data for training with the Mixture Prediction loss, which helps in efficient retrieval when the query belongs to an unseen domain. These losses are incorporated on the SE-ResNet50 backbone to obtain SnMpNet. Extensive experiments on two large-scale datasets, Sketchy Extended and DomainNet, and thorough comparisons with state-of-the-art justify the effectiveness of the proposed model.