Back

DeepFashion2

A versatile benchmark for clothing image understanding

DeepFashion2

DeepFashion2 is a comprehensive fashion dataset. It contains 491K diverse images of 13 popular clothing categories from both commercial shopping stores and consumers. It totally has 801K clothing clothing items, where each item in an image is labeled with scale, occlusion, zoom-in, viewpoint, category, style, bounding box, dense landmarks and per-pixel mask.There are also 873K Commercial-Consumer clothes pairs. The dataset is split into a training set (391K images), a validation set (34k images), and a test set (67k images).

View this Dataset
->
View author website
Task
Image Classification
Annotation Types
Classification Tags
9
Items
13
Classes
491000
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
Research Only