DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

By Yuying Ge, Ruimao Zhang, Lingyun Wu, Xiaogang Wang, Xiaoou Tang, Ping Luo. 2019

435 citations recorded by the source corpus.

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∼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 8× 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. DeepFashion2 Dataset will be released at : https://github.com/switchablenorms/DeepFashion2

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization (2020, methodology): “DFR leverages the metadata from DeepFashion2 (Ge et al., 2019) to systematically shift object occlusion, orientation, zoom, and scale at test time.”
Incremental Few-Shot Object Detection (2020, neutral): “(3) We perform extensive experiments on both standard object detection (COCO [29], PASCAL VOC [12]) and fashion landmark detection (DeepFashion2 [15]) tasks.”
Google Landmarks Dataset v2 – A Large-Scale Benchmark for Instance-Level Recognition and Retrieval (2020, background): “For example: logos [19, 30, 31, 47], cars [8, 63, 65], products [38, 21, 59, 51], artwork [2, 16], among others [11].”
M5Product: A Multi-modal Pretraining Benchmark for E-commercial Product Downstream Tasks (2021, background): “Although there are some E-commerce product datasets, these data are only specialized on the fashion domain [6, 11, 12].”
Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “flowers [45], vegetables [46], fruits [46], foods [47], fashion [6], [33], [38], retail products [5], [48], etc.”
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation (2020, methodology): “Color [37] 10,000 pedestrian 24 LabelMeFacade [38] 395 building 25 UT Zappos50K [39] 10,000 shoes 26 TRANCOS [40] 1,244 traffic 27 FGVC [40] 10,000 aeroplane 28 Mall Dataset [41] 2,000 mall 29 Chars74K [42] 7,705 character 30 DomainNet [8] 10,000 painting 31 Paris Dataset [43] 3,187 street 32 Domain”
Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content (2020, background): “Most of the existing works focus on clothing compatibility and matching learning [25, 17, 39], clothing landmark detection [29, 44, 8, 24], and fashion image analysis [14, 11, 27].”