This paper strives to learn fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute among fashion items, which has potential values in many fashion related applications such as fashion copyright protection. To this end, we propose an Attribute-Specific Embedding Network (ASEN) to jointly learn multiple attribute-specific embeddings in an end-to-end manner, thus measure the fine-grained similarity in the corresponding space. With two attention modules, i.e., Attribute-aware Spatial Attention and Attribute-aware Channel Attention, ASEN is able to locate the related regions and capture the essential patterns under the guidance of the specified attribute, thus make the learned attribute-specific embeddings better reflect the fine-grained similarity. Extensive experiments on four fashion-related datasets show the effectiveness of ASEN for fine-grained fashion similarity learning and its potential for fashion reranking.
@article{arxiv.2002.02814,
title = {Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network},
author = {Zhe Ma and Jianfeng Dong and Yao Zhang and Zhongzi Long and Yuan He and Hui Xue and Shouling Ji},
journal= {arXiv preprint arXiv:2002.02814},
year = {2020}
}
Comments
16 pages, 13 figutes. Accepted by AAAI 2020. Code and data are available at https://github.com/Maryeon/asen