Garment Attribute Manipulation with Multi-level Attention
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914950034751488 |
|---|---|
| author | Casula, Vittorio Berlincioni, Lorenzo Cultrera, Luca Becattini, Federico Pero, Chiara Bisogni, Carmen Bertini, Marco Del Bimbo, Alberto |
| author_facet | Casula, Vittorio Berlincioni, Lorenzo Cultrera, Luca Becattini, Federico Pero, Chiara Bisogni, Carmen Bertini, Marco Del Bimbo, Alberto |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10206 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Garment Attribute Manipulation with Multi-level Attention Casula, Vittorio Berlincioni, Lorenzo Cultrera, Luca Becattini, Federico Pero, Chiara Bisogni, Carmen Bertini, Marco Del Bimbo, Alberto Computer Vision and Pattern Recognition 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. |
| title | Garment Attribute Manipulation with Multi-level Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10206 |