Deep Learning for Human Parsing: A Survey

TL;DR

This survey reviews deep learning methods for human parsing, categorizing approaches into five groups, analyzing their strengths and weaknesses, and discussing datasets, performance, and future research directions in the field.

Contribution

It provides a comprehensive analysis of state-of-the-art deep learning techniques for human parsing, categorizing methods and highlighting their comparative advantages.

Findings

Structured architectures exploit human body hierarchies.

Graph-based networks capture global information effectively.

Context-aware and LSTM methods enhance pixel-level understanding.

Abstract

Human parsing is a key topic in image processing with many applications, such as surveillance analysis, human-robot interaction, person search, and clothing category classification, among many others. Recently, due to the success of deep learning in computer vision, there are a number of works aimed at developing human parsing algorithms using deep learning models. As methods have been proposed, a comprehensive survey of this topic is of great importance. In this survey, we provide an analysis of state-of-the-art human parsing methods, covering a broad spectrum of pioneering works for semantic human parsing. We introduce five insightful categories: (1) structure-driven architectures exploit the relationship of different human parts and the inherent hierarchical structure of a human body, (2) graph-based networks capture the global information to achieve an efficient and complete human body analysis, (3) context-aware networks explore useful contexts across all pixel to characterize a pixel of the corresponding class, (4) LSTM-based methods can combine short-distance and long-distance spatial dependencies to better exploit abundant local and global contexts, and (5) combined auxiliary information approaches use related tasks or supervision to improve network performance. We also discuss the advantages/disadvantages of the methods in each category and the relationships between methods in different categories, examine the most widely used datasets, report performances, and discuss promising future research directions in this area.