Single-stage Multi-human Parsing via Point Sets and Center-based Offsets
This addresses the computational inefficiency in existing two-stage methods for multi-human parsing, offering a more efficient solution for computer vision applications.
The paper tackles the multi-human parsing problem by proposing a single-stage deep architecture that decouples it into locating human bodies and parts using point features and offsets, eliminating the need for grouping. It achieves state-of-the-art results on the MHPv2.0 dataset with improvements of 2.1% in AP50p, 1.0% in APvolp, and 1.2% in PCP50, while requiring fewer training epochs and a simpler model.
This work studies the multi-human parsing problem. Existing methods, either following top-down or bottom-up two-stage paradigms, usually involve expensive computational costs. We instead present a high-performance Single-stage Multi-human Parsing (SMP) deep architecture that decouples the multi-human parsing problem into two fine-grained sub-problems, i.e., locating the human body and parts. SMP leverages the point features in the barycenter positions to obtain their segmentation and then generates a series of offsets from the barycenter of the human body to the barycenters of parts, thus performing human body and parts matching without the grouping process. Within the SMP architecture, we propose a Refined Feature Retain module to extract the global feature of instances through generated mask attention and a Mask of Interest Reclassify module as a trainable plug-in module to refine the classification results with the predicted segmentation. Extensive experiments on the MHPv2.0 dataset demonstrate the best effectiveness and efficiency of the proposed method, surpassing the state-of-the-art method by 2.1% in AP50p, 1.0% in APvolp, and 1.2% in PCP50. In particular, the proposed method requires fewer training epochs and a less complex model architecture. We will release our source codes, pretrained models, and online demos to facilitate further studies.