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

arXiv: https://arxiv.org/abs/1901.07973 · HTML: https://mlsanity.com/paper/1901.07973/

## Key facts

- Cited by 134 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2019.

## Built on by (most cited first, 30 of 134)

- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion](https://mlsanity.com/paper/2304.06025/) (2023)
- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion](https://mlsanity.com/paper/2311.12052/) (2023)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models](https://mlsanity.com/paper/2407.15886/) (2024)
- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks](https://mlsanity.com/paper/2501.15891/) (2025)
- [UniHCP: A Unified Model for Human-Centric Perceptions](https://mlsanity.com/paper/2303.02936/) (2023)
- [Linear Spaces of Meanings: Compositional Structures in Vision-Language Models](https://mlsanity.com/paper/2302.14383/) (2023)
- [Diffusion Model-Based Video Editing: A Survey](https://mlsanity.com/paper/2407.07111/) (2024)
- [3D Clothed Human Reconstruction in the Wild](https://mlsanity.com/paper/2207.10053/) (2022)
- [BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training](https://mlsanity.com/paper/2408.06047/) (2024)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images](https://mlsanity.com/paper/2311.16094/) (2023)
- [REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos](https://mlsanity.com/paper/2305.14236/) (2023)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2306.15521/) (2023)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [X-Pose: Detecting Any Keypoints](https://mlsanity.com/paper/2310.08530/) (2023)
- [Dressing in the Wild by Watching Dance Videos](https://mlsanity.com/paper/2203.15320/) (2022)
- [Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics](https://mlsanity.com/paper/2502.03449/) (2025)
- [TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models](https://mlsanity.com/paper/2411.18350/) (2024)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation](https://mlsanity.com/paper/2303.16382/) (2023)
- [When Does Perceptual Alignment Benefit Vision Representations?](https://mlsanity.com/paper/2410.10817/) (2024)
- [Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification](https://mlsanity.com/paper/2204.02611/) (2022)

## Abstract (arXiv)

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, viewpoint, occlusion, bounding box, dense landmarks and masks. There are also 873K Commercial-Consumer clothes pairs. 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 DeepFashion2.