Learning Hierarchical Representations with Spike-and-Slab Inception Network
Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expres...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/19/6382 |
_version_ | 1797515808755154944 |
---|---|
author | Weizheng Qiao Xiaojun Bi |
author_facet | Weizheng Qiao Xiaojun Bi |
author_sort | Weizheng Qiao |
collection | DOAJ |
description | Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expression, further resulting in insufficient feature mining. In view of this issue, researchers incessantly deepened the network, bringing parameter redundancy and model over-fitting. Hence, whether we can employ this efficient deep neural network architecture to improve CNN and enhance the capacity of image recognition task still remains unknown. In this paper, we introduce spike-and-slab units to the modified inception module, enabling our model to capture dual latent variables and the average and covariance information. This operation further enhances the robustness of our model to variations of image intensity without increasing the model parameters. The results of several tasks demonstrated that dual variable operations can be well-integrated into inception modules, and excellent results have been achieved. |
first_indexed | 2024-03-10T06:52:30Z |
format | Article |
id | doaj.art-d153a4e82661450b8eb04f149a8a884a |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T06:52:30Z |
publishDate | 2021-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-d153a4e82661450b8eb04f149a8a884a2023-11-22T16:45:21ZengMDPI AGSensors1424-82202021-09-012119638210.3390/s21196382Learning Hierarchical Representations with Spike-and-Slab Inception NetworkWeizheng Qiao0Xiaojun Bi1College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Information Engineering, Minzu University of China, Beijing 100091, ChinaRecently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expression, further resulting in insufficient feature mining. In view of this issue, researchers incessantly deepened the network, bringing parameter redundancy and model over-fitting. Hence, whether we can employ this efficient deep neural network architecture to improve CNN and enhance the capacity of image recognition task still remains unknown. In this paper, we introduce spike-and-slab units to the modified inception module, enabling our model to capture dual latent variables and the average and covariance information. This operation further enhances the robustness of our model to variations of image intensity without increasing the model parameters. The results of several tasks demonstrated that dual variable operations can be well-integrated into inception modules, and excellent results have been achieved.https://www.mdpi.com/1424-8220/21/19/6382convolutional neural networksinception modulespike-and-slab unitsdual variable operations |
spellingShingle | Weizheng Qiao Xiaojun Bi Learning Hierarchical Representations with Spike-and-Slab Inception Network Sensors convolutional neural networks inception module spike-and-slab units dual variable operations |
title | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_full | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_fullStr | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_full_unstemmed | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_short | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_sort | learning hierarchical representations with spike and slab inception network |
topic | convolutional neural networks inception module spike-and-slab units dual variable operations |
url | https://www.mdpi.com/1424-8220/21/19/6382 |
work_keys_str_mv | AT weizhengqiao learninghierarchicalrepresentationswithspikeandslabinceptionnetwork AT xiaojunbi learninghierarchicalrepresentationswithspikeandslabinceptionnetwork |