Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing

TL;DR

This paper introduces a large-scale multi-human parsing dataset and a novel deep nested adversarial network model that significantly improves understanding of humans in crowded scenes, aiding tasks like group behavior analysis and re-identification.

Contribution

The paper presents a new comprehensive dataset for multi-human parsing and a novel nested adversarial network architecture that advances state-of-the-art performance.

Findings

NAN outperforms existing methods on MHP and other datasets.

The MHP dataset contains 25,403 annotated images with 58 semantic categories.

The nested adversarial structure effectively learns joint semantic saliency, parsing, and clustering.

Abstract

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. To this end, models need to comprehensively perceive the semantic information and the differences between instances in a multi-human image, which is recently defined as the multi-human parsing task. In this paper, we present a new large-scale database "Multi-Human Parsing (MHP)" for algorithm development and evaluation, and advances the state-of-the-art in understanding humans in crowded scenes. MHP contains 25,403 elaborately annotated images with 58 fine-grained semantic category labels, involving 2-26 persons per image and captured in real-world scenes from various viewpoints, poses, occlusion, interactions and background. We further propose a novel deep Nested Adversarial Network (NAN) model for multi-human parsing. NAN consists of three Generative Adversarial Network (GAN)-like sub-nets, respectively performing semantic saliency prediction, instance-agnostic parsing and instance-aware clustering. These sub-nets form a nested structure and are carefully designed to learn jointly in an end-to-end way. NAN consistently outperforms existing state-of-the-art solutions on our MHP and several other datasets, and serves as a strong baseline to drive the future research for multi-human parsing.