Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917674269802496 |
|---|---|
| author | Wu, Yiming Li, Hangfei Wang, Fangfang Zhang, Yilong Liang, Ronghua |
| author_facet | Wu, Yiming Li, Hangfei Wang, Fangfang Zhang, Yilong Liang, Ronghua |
| contents | In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15451 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval Wu, Yiming Li, Hangfei Wang, Fangfang Zhang, Yilong Liang, Ronghua Computer Vision and Pattern Recognition Information Retrieval Multimedia In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods. |
| title | Self-distilled Dynamic Fusion Network for Language-based Fashion Retrieval |
| topic | Computer Vision and Pattern Recognition Information Retrieval Multimedia |
| url | https://arxiv.org/abs/2405.15451 |