Devil in the Details: Towards Accurate Single and Multiple Human Parsing

Abstract

Human parsing has received considerable interest due to its wide application potentials. Nevertheless, it is still unclear how to develop an accurate human parsing system in an efficient and elegant way. In this paper, we identify several useful properties, including feature resolution, global context information and edge details, and perform rigorous analyses to reveal how to leverage them to benefit the human parsing task. The advantages of these useful properties finally result in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing. Our CE2P is end-to-end trainable and can be easily adopted for conducting multiple human parsing. Benefiting the superiority of CE2P, we achieved the 1st places on all three human parsing benchmarks. Without any bells and whistles, we achieved 56.50\% (mIoU), 45.31\% (mean $A{P}^r$) and 33.34\% ($A{P}_{0.5}^p$) in LIP, CIHP and MHP v2.0, which outperform the state-of-the-arts more than 2.06\%, 3.81\% and 1.87\%, respectively. We hope our CE2P will serve as a solid baseline and help ease future research in single/multiple human parsing. Code has been made available at \url{https://github.com/liutinglt/CE2P}.

References in corpus (6)

• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Simultaneous Detection and Segmentation
• Multiple-Human Parsing in the Wild
• Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
• Joint Object and Part Segmentation using Deep Learned Potentials
• Instance-level Human Parsing via Part Grouping Network

Cited by in corpus (20)

• High-Resolution Representations for Labeling Pixels and Regions
• OCNet: Object Context Network for Scene Parsing
• Deep High-Resolution Representation Learning for Visual Recognition
• Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing
• Interlaced Sparse Self-Attention for Semantic Segmentation
• Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• A High-Efficiency Framework for Constructing Large-Scale Face Parsing Benchmark
• Hierarchical Human Parsing with Typed Part-Relation Reasoning
• Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
• CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
• A Unified Efficient Pyramid Transformer for Semantic Segmentation
• Anti-Confusing: Region-Aware Network for Human Pose Estimation
• Adversarial Semantic Data Augmentation for Human Pose Estimation
• Quality-Aware Network for Human Parsing
• Human De-occlusion: Invisible Perception and Recovery for Humans
• Self-Learning with Rectification Strategy for Human Parsing
• C-DLinkNet: considering multi-level semantic features for human parsing
• GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling
• 3rd Place Solution for Short-video Face Parsing Challenge