Nondiscriminatory Treatment: a straightforward framework for multi-human parsing

TL;DR

This paper introduces NTHP, an end-to-end, box-free multi-human parsing framework that treats humans and parts uniformly, achieving superior results by directly predicting instance masks and associating parts with humans.

Contribution

The paper proposes a novel nondiscriminatory, end-to-end approach for multi-human parsing that simplifies the pipeline and improves performance over existing methods.

Findings

Outperforms state-of-the-art on MHP v2.0 and PASCAL-Person-Part datasets

Introduces a unified treatment of humans and parts in parsing

Achieves higher accuracy with a box-free, end-to-end model

Abstract

Multi-human parsing aims to segment every body part of every human instance. Nearly all state-of-the-art methods follow the "detection first" or "segmentation first" pipelines. Different from them, we present an end-to-end and box-free pipeline from a new and more human-intuitive perspective. In training time, we directly do instance segmentation on humans and parts. More specifically, we introduce a notion of "indiscriminate objects with categorie" which treats humans and parts without distinction and regards them both as instances with categories. In the mask prediction, each binary mask is obtained by a combination of prototypes shared among all human and part categories. In inference time, we design a brand-new grouping post-processing method that relates each part instance with one single human instance and groups them together to obtain the final human-level parsing result. We name our method as Nondiscriminatory Treatment between Humans and Parts for Human Parsing (NTHP). Experiments show that our network performs superiorly against state-of-the-art methods by a large margin on the MHP v2.0 and PASCAL-Person-Part datasets.