Self-Learning with Rectification Strategy for Human Parsing
CVPR(2020)
摘要
In this paper, we solve the sample shortage problem in the human parsing task. We begin with the self-learning strategy, which generates pseudo-labels for unlabeled data to retrain the model. However, directly using noisy pseudo-labels will cause error amplification and accumulation. Considering the topology structure of human body, we propose a trainable graph reasoning method that establishes internal structural connections between graph nodes to correct two typical errors in the pseudo-labels, i.e., the global structural error and the local consistency error. For the global error, we first transform category-wise features into a high-level graph model with coarse-grained structural information, and then decouple the high-level graph to reconstruct the category features. The reconstructed features have a stronger ability to represent the topology structure of the human body. Enlarging the receptive field of features can effectively reducing the local error. We first project feature pixels into a local graph model to capture pixel-wise relations in a hierarchical graph manner, then reverse the relation information back to the pixels. With the global structural and local consistency modules, these errors are rectified and confident pseudo-labels are generated for retraining. Extensive experiments on the LIP and the ATR datasets demonstrate the effectiveness of our global and local rectification modules. Our method outperforms other state-of-the-art methods in supervised human parsing tasks.
更多查看译文
关键词
rectification strategy,self-learning strategy,unlabeled data,noisy pseudolabels,error amplification,topology structure,human body,graph nodes,global structural error,consistency error,category-wise features,high-level graph model,coarse-grained structural information,category features,pixel-wise relations,hierarchical graph manner,global structural consistency modules,global rectification modules,supervised human parsing tasks,graph reasoning method,feature reconstructed
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络