DAtRNet: Disentangling Fashion Attribute Embedding for Substitute Item Retrieval

Abstract

Interactive substitute recommendation for fashion products improves the online retail customer experience. Traditional fashion search platforms incorporate product metadata between the query products and the products to be retrieved. In this paper, we propose DAtRNet, an attribute representation network to disentangle the features in the query product. It is used to recommend attribute-aware substitute items based on the conditional similarity of the retrieved products. The proposed architecture relies on attribute-level similarity providing a fine-grained recommendation. In addition, a concurrent axial attention mechanism is proposed that generates global information embedding and adaptively re-calibrates the soft attention masks. Overall, the end-to-end framework enables the system to disentangle the attribute features and independently deals with them to enhance its flexibility towards one or multiple attributes. The proposed method outperforms the state-of- the-art by a significant margin.

Cite

Text

Bhattacharya et al. "DAtRNet: Disentangling Fashion Attribute Embedding for Substitute Item Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00253

Markdown

[Bhattacharya et al. "DAtRNet: Disentangling Fashion Attribute Embedding for Substitute Item Retrieval." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/bhattacharya2022cvprw-datrnet/) doi:10.1109/CVPRW56347.2022.00253

BibTeX

@inproceedings{bhattacharya2022cvprw-datrnet,
  title     = {{DAtRNet: Disentangling Fashion Attribute Embedding for Substitute Item Retrieval}},
  author    = {Bhattacharya, Gaurab and Kilari, Nikhil and Gubbi, Jayavardhana and V, Bagya Lakshmi and Pal, Arpan and P, Balamuralidhar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {2282-2286},
  doi       = {10.1109/CVPRW56347.2022.00253},
  url       = {https://mlanthology.org/cvprw/2022/bhattacharya2022cvprw-datrnet/}
}