Universal Cross-Domain Retrieval: Generalizing Across Classes and Domains

08/18/2021
by   Soumava Paul, et al.
0

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.

READ FULL TEXT

page 4

page 8

page 15

research
08/19/2022

TTT-UCDR: Test-time Training for Universal Cross-Domain Retrieval

Image retrieval is a niche problem in computer vision curated towards fi...
research
05/09/2023

Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval

Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to t...
research
02/13/2023

Correspondence-Free Domain Alignment for Unsupervised Cross-Domain Image Retrieval

Cross-domain image retrieval aims at retrieving images across different ...
research
03/12/2021

Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

Face recognition models trained under the assumption of identical traini...
research
03/31/2021

Deep Image Harmonization by Bridging the Reality Gap

Image harmonization has been significantly advanced with large-scale har...
research
05/06/2023

Cross-domain Augmentation Networks for Click-Through Rate Prediction

Data sparsity is an important issue for click-through rate (CTR) predict...
research
10/14/2022

Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization

Domain generalization (DG) enables generalizing a learning machine from ...

Please sign up or login with your details

Forgot password? Click here to reset