arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07409cs.CV
收藏

短视频人脸解析挑战赛第三名解决方案

3rd Place Solution for Short-video Face Parsing Challenge

Dalian University of Technology(大连理工大学)

Xiao Liu, Xiaofei Si, Jiangtao Xie

摘要:

这是一份简短的技术报告,介绍了Team Rat在CVPR 2021的第三人称上下文(PIC)研讨会和挑战赛中的短视频解析人脸解析跟踪解决方案。在这份报告中,我们提出了一个边缘感知网络(EANet),使用边缘信息来细化分割边缘。为了进一步得到更精细的边缘结果,我们引入了边缘注意损失,只计算边缘上的交叉熵,可以有效地减少边缘周围的分类误差,得到更光滑的边界。在第三人称上下文(PIC)研讨会和挑战赛的短视频人脸解析中,EANet算法利用边缘信息和边缘注意力损失,获得了86.16%的准确率,排名第三。

英文摘要:

This is a short technical report introducing the solution of Team Rat for Short-video Parsing Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. In this report, we propose an Edge-Aware Network (EANet) that uses edge information to refine the segmentation edge. To further obtain the finer edge results, we introduce edge attention loss that only compute cross entropy on the edges, it can effectively reduce the classification error around edge and get more smooth boundary. Benefiting from the edge information and edge attention loss, the proposed EANet achieves 86.16\% accuracy in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the third place.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑