Fashion Image Retrieval With Multi-granular Alignment

Abstract

Fashion image retrieval task aims to search relevant clothing items of a query image from the gallery. The previous recipes focus on designing different distance-based loss functions, pulling relevant pairs to be close and pushing irrelevant images apart. However, these methods ignore fine-grained features (e.g. neckband, cuff) of clothing images. In this paper, we propose a novel fashion image retrieval method leveraging both global and fine-grained features, dubbed Multi-Granular Alignment (MGA). Specifically, we design a Fine-Granular Aggregator(FGA) to capture and aggregate detailed patterns. Then we propose Attention-based Token Alignment (ATA) to align image features at the multi-granular level in a coarse-to-fine manner. To prove the effectiveness of our proposed method, we conduct experiments on two sub-tasks (In-Shop & Consumer2Shop) of the public fashion datasets DeepFashion. The experimental results show that our MGA outperforms the state-of-the-art methods by 1.8% and 0.6%

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhu2023fashion

Related papers

• Mmfl-net: Multi-scale And Multi-granularity Feature Learning For Cross-domain Fashion Retrieval (2022)5.84
• Attribute-guided Multi-level Attention Network For Fine-grained Fashion Retrieval (2022)7.74
• Fine-grained Apparel Classification And Retrieval Without Rich Annotations (2018)0.00
• Fashionbert: Text And Image Matching With Adaptive Loss For Cross-modal Retrieval (2020)15.16
• Semi-supervised Feature-level Attribute Manipulation For Fashion Image Retrieval (2019)0.00
• A Strong Baseline For Fashion Retrieval With Person Re-identification Models (2020)8.09
• Training And Challenging Models For Text-guided Fashion Image Retrieval (2022)0.00
• Fashion Retrieval Via Graph Reasoning Networks On A Similarity Pyramid (2019)14.19