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

2019-01-23 · CVPR 2019 6 · Yuying Ge, Ruimao Zhang, Lingyun Wu, Xiaogang Wang, Xiaoou Tang, Ping Luo

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.

📄 PDF Abstract BibTeX arXiv:1901.07973

Code (5)

switchablenorms/DeepFashion2 공식 구현

AlberetOZ/WondeRobe_Clothes_test pytorch

SCP-173-cool/match_rcnn

ScaDS/Match-R-CNN-Repoduction pytorch

ccc013/DeepLearning_Notes tf

Tasks

Pose Estimation Retrieval Semantic Segmentation

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…

Mask R-CNN Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an…

Aggregation and Finetuning for Clothes Landmark Detection

2020-05-01 · Tzu-Heng Lin

Landmark detection for clothes is a fundamental problem for many applications. In this paper, a new training scheme for clothes landmark detection: $\textit{Aggregation and Finetuning}$, is proposed. We investigate the h…

Clothes Landmark Detection

DeepMark++: Real-time Clothing Detection at the Edge

2020-06-01 · Alexey Sidnev, Alexander Krapivin, Alexey Trushkov, Ekaterina Krasikova 외

Clothing recognition is the most fundamental AI application challenge within the fashion domain. While existing solutions offer decent recognition accuracy, they are generally slow and require significant computational r…

Clothes Landmark Detection Keypoint Estimation

Efficient grouping for keypoint detection

2020-10-23 · Alexey Sidnev, Ekaterina Krasikova, Maxim Kazakov

The success of deep neural networks in the traditional keypoint detection task encourages researchers to solve new problems and collect more complex datasets. The size of the DeepFashion2 dataset poses a new challenge on…

Keypoint Detection Pose Estimation

Improving Apparel Detection with Category Grouping and Multi-grained Branches

2021-01-17 · Qing Tian, Sampath Chanda, K C Amit Kumar, Douglas Gray

Training an accurate object detector is expensive and time-consuming. One main reason lies in the laborious labeling process, i.e., annotating category and bounding box information for all instances in every image. In th…

Object

DeepMark: One-Shot Clothing Detection

2019-10-02 · Alexey Sidnev, Alexey Trushkov, Maxim Kazakov, Ivan Korolev 외

The one-shot approach, DeepMark, for fast clothing detection as a modification of a multi-target network, CenterNet, is proposed in the paper. The state-of-the-art accuracy of 0.723 mAP for bounding box detection task an…