Quality-Aware Network for Human Parsing

2021-03-10 · Lu Yang, Qing Song, Zhihui Wang, Zhiwei Liu, Songcen Xu, Zhihao LI

How to estimate the quality of the network output is an important issue, and currently there is no effective solution in the field of human parsing. In order to solve this problem, this work proposes a statistical method based on the output probability map to calculate the pixel quality information, which is called pixel score. In addition, the Quality-Aware Module (QAM) is proposed to fuse the different quality information, the purpose of which is to estimate the quality of human parsing results. We combine QAM with a concise and effective network design to propose Quality-Aware Network (QANet) for human parsing. Benefiting from the superiority of QAM and QANet, we achieve the best performance on three multiple and one single human parsing benchmarks, including CIHP, MHP-v2, Pascal-Person-Part and LIP. Without increasing the training and inference time, QAM improves the AP$^\text{r}$ criterion by more than 10 points in the multiple human parsing task. QAM can be extended to other tasks with good quality estimation, e.g. instance segmentation. Specifically, QAM improves Mask R-CNN by ~1% mAP on COCO and LVISv1.0 datasets. Based on the proposed QAM and QANet, our overall system wins 1st place in CVPR2019 COCO DensePose Challenge, and 1st place in Track 1 & 2 of CVPR2020 LIP Challenge. Code and models are available at https://github.com/soeaver/QANet.

📄 PDF Abstract BibTeX arXiv:2103.05997

Code (1)

soeaver/QANet 공식 구현 pytorch

Tasks

Human Parsing Instance Segmentation 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 $x$…

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…

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…

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…

AIParsing: Anchor-free Instance-level Human Parsing

2022-07-14 · Sanyi Zhang, Xiaochun Cao, Guo-Jun Qi, Zhanjie Song 외

Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address these tw…

Human Parsing object-detection Object Detection

Quality-Aware Network for Face Parsing

2021-06-14 · Lu Yang, Qing Song, Xueshi Xin, Wenhe Jia 외

This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. Face parsing has rece…

Face Parsing Human Parsing

Clicking Matters:Towards Interactive Human Parsing

2021-11-11 · Yutong Gao, Liqian Liang, Congyan Lang, Songhe Feng 외

In this work, we focus on Interactive Human Parsing (IHP), which aims to segment a human image into multiple human body parts with guidance from users' interactions. This new task inherits the class-aware property of hum…

Human Parsing Image Segmentation Semantic Segmentation

Multiple-Human Parsing in the Wild

2017-05-19 · Jianshu Li, Jian Zhao, Yunchao Wei, Congyan Lang 외

Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild. Existing works on human parsing mainly …

Human Parsing Multi-Human Parsing

RepParser: End-to-End Multiple Human Parsing with Representative Parts

2022-08-27 · Xiaojia Chen, Xuanhan Wang, Lianli Gao, Jingkuan Song

Existing methods of multiple human parsing usually adopt a two-stage strategy (typically top-down and bottom-up), which suffers from either strong dependence on prior detection or highly computational redundancy during p…

Human Detection Human Parsing