DeepFashion数据集，一个大型服装数据集

We contribute DeepFashion database, a large-scale clothes database, which has several appealing properties: 1、First, DeepFashion contains over 800,000 diverse fashion images ranging from well-posed shop images to unconstrained consumer photos, constituting the largest visual fashion analysis database. 2、Second, DeepFashion is annotated with rich information of clothing items. Each image in this dataset is labeled with 50 categories, 1,000 descriptive attributes, bounding box and clothing landmarks. 3、Third, DeepFashion contains over 300,000 cross-pose/cross-domain image pairs. 4、Four benchmarks are developed using the DeepFashion database, including Attribute Prediction, Consumer-to-shop Clothes Retrieval, In-shop Clothes Retrieval, and Landmark Detection. The data and annotations of these benchmarks can be also employed as the training and test sets for the following computer vision tasks, such as Clothes Detection, Clothes Recognition, and Image Retrieval. Please read Download Instructions below to access the dataset. 1、The DeepFashion is available for non-commercial research purposes only. Please contact Ping Luo and Ziwei Liu for questions about the dataset.

本研究贡献了DeepFashion数据库（DeepFashion），这是一款大规模服装数据库，具备多项引人瞩目的特性：
1、该数据库包含超过80万张多样化的时尚图像，涵盖规范摆拍的商品展示图与无约束条件下的消费者实拍照片，是目前规模最大的视觉时尚分析数据库。
2、该数据库为每件服装单品标注了丰富的标注信息：数据集中的每张图像均被标注了50个服装类别、1000项描述性属性、边界框（bounding box）以及服装关键点（clothing landmarks）。
3、该数据库包含超过30万张跨姿态/跨域图像对。
4、基于DeepFashion数据库构建了四项基准评测任务，涵盖属性预测（Attribute Prediction）、消费者图-商品图服装检索（Consumer-to-shop Clothes Retrieval）、店内服装检索（In-shop Clothes Retrieval）以及关键点检测（Landmark Detection）。上述基准评测任务的数据集与标注信息，还可作为服装检测（Clothes Detection）、服装识别（Clothes Recognition）、图像检索等计算机视觉任务的训练集与测试集使用。
请参阅下文的下载说明以获取该数据集。
1、DeepFashion数据库仅可用于非商业性研究用途。若对该数据集有任何疑问，请联系Ping Luo与Ziwei Liu。