Human parsing is the task of segmenting a human image into different fine-grained semantic parts such as head, torso, arms and legs.
( Image credit: Multi-Human-Parsing (MHP) )
Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.
#21 best model for Semantic Segmentation on Cityscapes test
Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis, person re-identification and autonomous driving, etc.
SOTA for Multi-Human Parsing on MHP v2.0
In this paper, we present a novel method to generate synthetic human part segmentation data using easily-obtained human keypoint annotations.
#4 best model for Human Part Segmentation on PASCAL-Person-Part (using extra training data)
Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass.
#2 best model for Human Part Segmentation on CIHP
To tackle the problem of learning with label noises, this work introduces a purification strategy, called Self-Correction for Human Parsing (SCHP), to progressively promote the reliability of the supervised labels as well as the learned models.
SOTA for Semantic Segmentation on LIP val
Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance.
SOTA for Human Part Segmentation on CIHP
By distilling universal semantic graph representation to each specific task, Graphonomy is able to predict all levels of parsing labels in one system without piling up the complexity.