In the rapidly evolving field of online fashion shopping, the need for more personalized and interactive image retrieval systems has become paramount. Existing methods often struggle with precisely manipulating specific garment attributes without inadvertently affecting others. To address this challenge, we propose GAMMA (Garment Attribute Manipulation with Multi-level Attention), a novel framework that integrates attribute-disentangled representations with a multi-stage attention-based architecture. GAMMA enables targeted manipulation of fashion image attributes, allowing users to refine their searches with high accuracy. By leveraging a dual-encoder Transformer and memory block, our model achieves state-of-the-art performance on popular datasets like Shopping100k and DeepFashion.
@article{arxiv.2409.10206,
title = {Garment Attribute Manipulation with Multi-level Attention},
author = {Vittorio Casula and Lorenzo Berlincioni and Luca Cultrera and Federico Becattini and Chiara Pero and Carmen Bisogni and Marco Bertini and Alberto Del Bimbo},
journal= {arXiv preprint arXiv:2409.10206},
year = {2024}
}
Comments
Accepted for publication at the ECCV 2024 workshop FashionAI