Universal Cross-domain Retrieval: Generalizing Across Classes And Domains

Abstract

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,

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keypaul2021universal

Related papers

• Test-time Training For Data-efficient UCDR (2022)0.00
• Multimodal Unsupervised Domain Generalization By Retrieving Across The Modality Gap (2024)1.81
• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00
• Preserving Semantic Neighborhoods For Robust Cross-modal Retrieval (2020)10.07
• CMIR-NET : A Deep Learning Based Model For Cross-modal Retrieval In Remote Sensing (2019)13.34
• Syncdr : Training Cross Domain Retrieval Models With Synthetic Data (2023)0.00
• Text-phase Synergy Network With Dual Priors For Unsupervised Cross-domain Image Retrieval (2026)0.00
• Efficient And Discriminative Image Feature Extraction For Universal Image Retrieval (2024)4.94