Deepfashion2: A Versatile Benchmark For Detection, Pose Estimation, Segmentation And Re-Identification Of Clothing Images
Computer Vision and Pattern Recognition(2019)
摘要
Understanding fashion images has been advanced by benchmarks with rich annotations such as DeepFashion, whose labels include clothing categories, landmarks, and consumer-commercial image pairs. However, DeepFashion has nonnegligible issues such as single clothing-item per image, sparse landmarks (4 similar to 8 only), and no per-pixel masks, making it had significant gap from real-world scenarios. We fill in the gap by presenting DeepFashion2 to address these issues. It is a versatile benchmark of four tasks including clothes detection, pose estimation, segmentation, and retrieval. It has 801K clothing items where each item has rich annotations such as style, scale, view- point, occlusion, bounding box, dense landmarks (e.g. 39 for 'long sleeve outwear' and 15 for 'vest'), and masks. There are also 873K Commercial-Consumer clothes pairs. The annotations of DeepFashion2 are much larger than its counterparts such as 8x of FashionAI Global Challenge. A strong baseline is proposed, called Match R-CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner. Extensive evaluations are conducted with different criterions in Deep- Fashion2.
更多查看译文
关键词
Datasets and Evaluation,Deep Learning,Recognition: Detection,Categorization,Retrieval
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要