.png){kind=icon}
Return
Stochastic subsampling with average pooling
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2026.114611.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a new module called stochastic average pooling (SAP). • SAP attains improved theoretical properties of consistency compared to Dropout. • SAP can be seamlessly integrated into existing architectures. • Experiments demonstrate that SAP improves performance across a variety of tasks. • Ablation studies were conducted to validate the module design of SAP.
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveRegularizing deep neural networks for medical image analysis with augmented batch normalization
PREAI
ShareSave
ShareSave no more
no more