Year: 2022
Type: article
Abstract: Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing convolutional blocks of the feature extractors, but less on the classifiers that exploit extracted features. In this work, we propose Split-and-Share Module (SSM), a classifier that splits a given feature into parts, which are partially shared by multiple sub-classifiers. Our intuition is that the more the features are shared, the more common they will become, and SSM can encourage such structural characteristics in the split features. SSM can be easily integrated into any architecture without bells and whistles. We have extensively validated the efficacy of SSM on ImageNet-1K classification task, and SSM has shown consistent and significant improvements over baseline architectures. In addition, we analyze the effect of SSM using the Grad-CAM visualization.
Source: Electronics
Authors: Jae-Min Lee, Min-Seok Seo, Dae-Han Kim, Sang-Woo Lee, Jong-Chan Park, Dong-Geol Choi
Institutions: Hanbat National University, Lunit (South Korea)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,094
Awards: G2244081277, G3770225351, G5561717160
OpenAlex ID: W3190571345