DeepFashion2

DeepFashion2 is a large-scale fashion image benchmark with comprehensive tasks and annotations. It contains 491K images, each of which is richly labeled with style, scale, occlusion, zooming, viewpoint, bounding box, dense landmarks and pose, pixel-level masks, and pair of images of identical item from consumer and commercial store.

Data and Resources

Cite this as

Changsheng Lu, Hao Zhu, Piotr Koniusz (2024). Dataset: DeepFashion2. https://doi.org/10.57702/q1fk0su1

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2101.06770
Citation
  • https://doi.org/10.48550/arXiv.2005.00419
Author Changsheng Lu
More Authors
Hao Zhu
Piotr Koniusz
Homepage https://github.com/switchablenorms/DeepFashion2