Garment Attribute Manipulation with Multi-Level Attention
Abstract
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.
Cite
Text
Casula et al. "Garment Attribute Manipulation with Multi-Level Attention." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91569-7_24Markdown
[Casula et al. "Garment Attribute Manipulation with Multi-Level Attention." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/casula2024eccvw-garment/) doi:10.1007/978-3-031-91569-7_24BibTeX
@inproceedings{casula2024eccvw-garment,
title = {{Garment Attribute Manipulation with Multi-Level Attention}},
author = {Casula, Vittorio and Berlincioni, Lorenzo and Cultrera, Luca and Becattini, Federico and Pero, Chiara and Bisogni, Carmen and Bertini, Marco and Del Bimbo, Alberto},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {385-401},
doi = {10.1007/978-3-031-91569-7_24},
url = {https://mlanthology.org/eccvw/2024/casula2024eccvw-garment/}
}