论文标题
翻新解析R-CNN，以精确多次解析
Renovating Parsing R-CNN for Accurate Multiple Human Parsing
论文作者
论文摘要
多次人类解析旨在将各个部分分割，并同时将每个部分与相应的实例相关联。由于人类外观，不同身体部位的语义歧义以及复杂的背景，这是一项非常具有挑战性的任务。通过分析多个人类解析任务，我们观察到以人为中心的全球感知和准确的实例解析评分对于获得高质量的结果至关重要。但是，最先进的方法对这些问题没有足够的关注。为了扭转这一现象，我们提出了翻新解析R-CNN（RP R-CNN），该解析引入了全球语义增强功能的特征金字塔网络，并将解析重新得分网络介入现有的高性能管道中。拟议的RP R-CNN采用了全球语义表示，以增强多尺度特征来生成人类解析图，并回归置信度得分以代表其质量。广泛的实验表明，RP R-CNN对CIHP和MHP-V2数据集上的最新方法表现出色。代码和型号可在https://github.com/soeaver/rp-r-cnn上找到。
Multiple human parsing aims to segment various human parts and associate each part with the corresponding instance simultaneously. This is a very challenging task due to the diverse human appearance, semantic ambiguity of different body parts, and complex background. Through analysis of multiple human parsing task, we observe that human-centric global perception and accurate instance-level parsing scoring are crucial for obtaining high-quality results. But the most state-of-the-art methods have not paid enough attention to these issues. To reverse this phenomenon, we present Renovating Parsing R-CNN (RP R-CNN), which introduces a global semantic enhanced feature pyramid network and a parsing re-scoring network into the existing high-performance pipeline. The proposed RP R-CNN adopts global semantic representation to enhance multi-scale features for generating human parsing maps, and regresses a confidence score to represent its quality. Extensive experiments show that RP R-CNN performs favorably against state-of-the-art methods on CIHP and MHP-v2 datasets. Code and models are available at https://github.com/soeaver/RP-R-CNN.
