Lrvs-fashion: Extending Visual Search With Referring Instructions

Abstract

This paper introduces a new challenge for image similarity search in the context of fashion, addressing the inherent ambiguity in this domain stemming from complex images. We present Referred Visual Search (RVS), a task allowing users to define more precisely the desired similarity, following recent interest in the industry. We release a new large public dataset, LRVS-Fashion, consisting of 272k fashion products with 842k images extracted from fashion catalogs, designed explicitly for this task. However, unlike traditional visual search methods in the industry, we demonstrate that superior performance can be achieved by bypassing explicit object detection and adopting weakly-supervised conditional contrastive learning on image tuples. Our method is lightweight and demonstrates robustness, reaching Recall at one superior to strong detection-based baselines against 2M distractors. The dataset is available at https://huggingface.co/datasets/Slep/LAION-RVS-Fashion .

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylepage2023lrvs

Related papers

• Efficient Discovery And Effective Evaluation Of Visual Perceptual Similarity: A Benchmark And Beyond (2023)4.52
• A Strong Baseline For Fashion Retrieval With Person Re-identification Models (2020)8.09
• Fashionvil: Fashion-focused Vision-and-language Representation Learning (2022)14.66
• Diversity In Fashion Recommendation Using Semantic Parsing (2019)10.21
• Training And Challenging Models For Text-guided Fashion Image Retrieval (2022)0.00
• Resedis: A Dataset For Referring-based Object Search Across Large-scale Image Collections (2025)0.00
• Partial Visual-semantic Embedding: Fashion Intelligence System With Sensitive Part-by-part Learning (2022)0.00
• Exploiting Latent Codes: Interactive Fashion Product Generation, Similar Image Retrieval, And Cross-category Recommendation Using Variational Autoencoders (2020)0.00