DeepFashion: Consumer-to-shop Clothes Retrieval


Multimedia Laboratory, The Chinese University of Hong Kong

Details

Consumer-to-shop Clothes Retrieval Benchmark evaluates the performance of consumer-to-shop Clothes Retrievel. This is a large subset of DeepFashion, containing cross-domain correspondences and variations in the wild. It contains

  • 33,881 number of clothing items;

  • 239,557 number of consumer/shop clothes images, and 195,540 cross-domain pairs;

  • Each image is annotated by bounding box, clothing type and source type.

Download


  • Consumer/Shop Images

  • High-Res Images

  • Pair Annotations

  • BBox & Landmark Annotations

  • Attribute Annotations


  • Type & Source Annotations


  • Train/Val/Test Partitions

Citation

@inproceedings{liuLQWTcvpr16DeepFashion,
 author = {Liu, Ziwei and Luo, Ping and Qiu, Shi and Wang, Xiaogang and Tang, Xiaoou},
 title = {DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations},
 booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 month = {June},
 year = {2016}
 }

Contact


Please contact Ziwei Liu for questions about the dataset.