论文阅读笔记:“MGFN:Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection”
sixwalter Lv6

论文阅读笔记:“MGFN:Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection”

网络框架

image-20230620161316631

核心亮点

Feature Amplification Mechanism (FAM)

image-20230620162407331

对于第i个视频的第t个片段,FAM会计算一个特征范数,他是在特征维度进行归一化

之后使用1d卷积调制范数信息来进行增强信息导出:

image-20230620162955067

Magnitude Contrastive Loss

之前经典方案是二元交叉熵损失:

论文提出了振幅对比损失:

image-20230620163836165

p,q是正常clip的索引,u,v是异常clip的索引,Ma是异常视频top-k高的特征振幅。如果p,u是一对正常,异常视频clip

image-20230620164614861

总体loss计算公式:

image-20230620165955867
  • Post title:论文阅读笔记:“MGFN:Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection”
  • Post author:sixwalter
  • Create time:2023-08-05 11:14:26
  • Post link:https://coelien.github.io/2023/08/05/paper-reading/paper_reading_065/
  • Copyright Notice:All articles in this blog are licensed under BY-NC-SA unless stating additionally.
 Comments