Training and challenging models for text-guided fashion image retrieval
This work addresses a multimodal retrieval challenge for apparel shopping, offering incremental advancements in dataset design and model fusion techniques.
The paper tackles the problem of retrieving fashion images based on a query image and modifying caption, introducing a new dataset (CFQ) and a modeling approach that achieves state-of-the-art performance on the Fashion IQ dataset, with improvements demonstrated through multimodal pretraining and a residual attention fusion mechanism.
Retrieving relevant images from a catalog based on a query image together with a modifying caption is a challenging multimodal task that can particularly benefit domains like apparel shopping, where fine details and subtle variations may be best expressed through natural language. We introduce a new evaluation dataset, Challenging Fashion Queries (CFQ), as well as a modeling approach that achieves state-of-the-art performance on the existing Fashion IQ (FIQ) dataset. CFQ complements existing benchmarks by including relative captions with positive and negative labels of caption accuracy and conditional image similarity, where others provided only positive labels with a combined meaning. We demonstrate the importance of multimodal pretraining for the task and show that domain-specific weak supervision based on attribute labels can augment generic large-scale pretraining. While previous modality fusion mechanisms lose the benefits of multimodal pretraining, we introduce a residual attention fusion mechanism that improves performance. We release CFQ and our code to the research community.