Syncdr : Training Cross Domain Retrieval Models With Synthetic Data

Abstract

In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's catalog. A standard approach for such a problem is learning a feature space of images where Euclidean distances reflect similarity. Even without human annotations, which may be expensive to acquire, prior methods function reasonably well using unlabeled images for training. Our problem constraint takes this further to scenarios where the two domains do not necessarily share any common categories in training data. This can occur when the two domains in question come from different versions of some biometric sensor recording identities of different people. We posit a simple solution, which is to generate synthetic data to fill in these missing category examples across domains. This, we do via category preserving translation of images from one visual domain

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymishra2023syncdr

Related papers

• Test-time Training For Data-efficient UCDR (2022)0.00
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Retrieval-guided Cross-view Image Synthesis (2024)0.00
• Retrieval Guided Unsupervised Multi-domain Image-to-image Translation (2020)6.77
• Caption-matching: A Multimodal Approach For Cross-domain Image Retrieval (2024)0.00
• Correspondence-free Domain Alignment For Unsupervised Cross-domain Image Retrieval (2023)9.23
• Graph-based Cross-domain Knowledge Distillation For Cross-dataset Text-to-image Person Retrieval (2025)3.58
• Semantic Feature Learning For Universal Unsupervised Cross-domain Retrieval (2024)0.00