OutfitTransformer: Outfit Representations for Fashion Recommendation
Abstract
Predicting outfit compatibility and retrieving complementary items are critical components for a fashion recommendation system. We present a scalable framework, OutfitTransformer, that learns compatibility of the entire out- fit and supports large-scale complementary item retrieval. We model outfits as an unordered set of items and leverage self-attention mechanism to learn the relationships between items. We train the framework using a proposed set-wise outfit ranking loss to generate a target item embedding given an outfit, and a target item specification. The generated target item embedding is then used to retrieve compatible items that match the outfit. Experimental results demonstrate that our approach outperforms state-of-the-art methods on compatibility prediction, fill-in-the-blank, and complementary item retrieval tasks.
Cite
Text
Sarkar et al. "OutfitTransformer: Outfit Representations for Fashion Recommendation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00249Markdown
[Sarkar et al. "OutfitTransformer: Outfit Representations for Fashion Recommendation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/sarkar2022cvprw-outfittransformer/) doi:10.1109/CVPRW56347.2022.00249BibTeX
@inproceedings{sarkar2022cvprw-outfittransformer,
title = {{OutfitTransformer: Outfit Representations for Fashion Recommendation}},
author = {Sarkar, Rohan and Bodla, Navaneeth and Vasileva, Mariya I. and Lin, Yen-Liang and Beniwal, Anurag and Lu, Alan and Medioni, Gérard G.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2022},
pages = {2262-2266},
doi = {10.1109/CVPRW56347.2022.00249},
url = {https://mlanthology.org/cvprw/2022/sarkar2022cvprw-outfittransformer/}
}