Sorry, you need to enable JavaScript to visit this website.

1-D Spatial Attention in Binarized Convolutional Neural Networks

DOI:
10.60864/c5te-1187
Citation Author(s):
Jungwoo Shin, Alberto A. Del Barrio
Submitted by:
WANSOO KIM
Last updated:
7 April 2024 - 9:12pm
Document Type:
Poster
Document Year:
2024
Event:
Paper Code:
MLSP-P21.9
 

This paper proposes a structure called SPBNet for enhancing binarized convolutional neural networks (BCNNs) using a low-cost 1-D spatial attention structure. Attention blocks can compensate for the performance drop in BCNNs. However, the hardware overhead of complex attention blocks can be a significant burden in BCNNs. The proposed attention block consists of low-cost 1-D height-wise and width-wise 1-D convolutions, It has the attention bias to adjust the effects of attended features in ×0.5 − ×1.5. In experiments, the proposed block used in ResNet18-based BCNNs improves Top-1 accuracy up to 2.7% over a baseline ReActNet on the CIFAR- 100 dataset. Notably, without using teacher-student training, the proposed structure can show comparable performance as the baseline ReActNetA using teacher-student training.

up
1 user has voted: WANSOO KIM

Comments