Self-Correction for Human Parsing
IEEE Transactions on Pattern Analysis and Machine Intelligence(2022)
摘要
Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g., human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearances are usually confusing for annotators, leading to incorrect labels in ground-truth masks. These label noises will inevitably harm the training process and decrease the performan...
更多查看译文
关键词
Training,Task analysis,Predictive models,Annotations,Semantics,Analytical models,Solid modeling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要