Nondiscriminatory Treatment: a straightforward framework for multi-human parsing
This addresses the problem of segmenting body parts in multi-human images for computer vision applications, presenting a novel approach that is not incremental.
The paper tackles multi-human parsing by proposing an end-to-end, box-free pipeline that treats humans and body parts as indiscriminate objects with categories, achieving superior performance against state-of-the-art methods on MHP v2.0 and PASCAL-Person-Part datasets.
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.