ULSAM icon indicating copy to clipboard operation
ULSAM copied to clipboard

Published 20 hours ago • verified publisher icon Nandan91
→

Metadata

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks

Results 2 ULSAM issues
Sort by recently updated
recently updated
newest added

about MaxPool

5 comment

@Nandan91 @rajatsaini0294 HI For each subspace, the input is HxWxG, through DW + MaxPool + PW, the **middle attention map** is HxWx1, then through Softmax + Expand, the **final attention...

foralliance avatar foralliance

ATTENTION VISUALIZATION

2 comment

I want to know how to creat ATTERTION VISUALIZATION map in your artical

lingyi-learning avatar lingyi-learning

← Metadata

77
Stars
15
Forks
Watchers

Owner

verified publisher icon Nandan91

Metadata

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks

Back