FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 1228-1236
DOI: 10.1609/aaai.v38i2.27885 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yanzhe Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).
Abstract (Originalsprache)
The goal of composed fashion image retrieval is to locate a target image based on a reference image and modified text. Recent methods utilize symmetric encoders (e.g., CLIP) pre-trained on large-scale non-fashion datasets. However, the input for this task exhibits an asymmetric nature, where the reference image contains rich content while the modified text is often brief. Therefore, methods employing symmetric encoders encounter a severe phenomenon: retrieval results dominated by reference images, leading to the oversight of modified text. We propose a Fashion Enhance-and-Refine Network (FashionERN) centered around two aspects: enhancing the text encoder and refining visual semantics. We introduce a Triple-branch Modifier Enhancement model, which injects relevant information from the reference image and aligns the modified text modality with the target image modality. Furthermore, we propose a Dual-guided Vision Refinement model that retains critical visual information through text-guided refinement and self-guided refinement processes. The combination of these two models significantly mitigates the reference dominance phenomenon, ensuring accurate fulfillment of modifier requirements. Comprehensive experiments demonstrate our approach's state-of-the-art performance on four commonly used datasets.
Zitieren
APA
Chen, Y., Zhong, H., He, X., Peng, Y., Zhou, J., & Cheng, L. (2024). FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1228-1236. https://doi.org/10.1609/aaai.v38i2.27885
Vancouver
Chen Y, Zhong H, He X, Peng Y, Zhou J, Cheng L. FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):1228-1236. doi:10.1609/aaai.v38i2.27885
BibTeX
@article{Chen2024,
author = {Chen, Yanzhe and Zhong, Huasong and He, Xiangteng and Peng, Yuxin and Zhou, Jiahuan and Cheng, Lele},
title = {FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {2},
pages = {1228--1236},
doi = {10.1609/aaai.v38i2.27885}
}
EUVIMED