Feature Fusion Framework Combining Attention Mechanism and Geometric Information
The imbalanced problem is common in the real world,and the highly-skewed distribution of imbalanced data seriously affects the performance of the model.In general,the imbalanced data affects the model performance from two aspects.On the one hand,the imbalance in sample size leads to more updates of...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-05-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-5-129.pdf |
| _version_ | 1797845048159633408 |
|---|---|
| author | DONG Qi-da, WANG Zhe, WU Song-yang |
| author_facet | DONG Qi-da, WANG Zhe, WU Song-yang |
| author_sort | DONG Qi-da, WANG Zhe, WU Song-yang |
| collection | DOAJ |
| description | The imbalanced problem is common in the real world,and the highly-skewed distribution of imbalanced data seriously affects the performance of the model.In general,the imbalanced data affects the model performance from two aspects.On the one hand,the imbalance in sample size leads to more updates of parameters in majority classes,which leads to the model biased to majority classes.On the other hand,the sample size of minority classes is too small,and the diversity is insufficient,which leads to the insufficient representation ability of the model.To solve these problems,this paper proposes a feature fusion framework combining attention mechanism and geometric information.Specifically,in the first stage,the model learns the semantic information and discriminative information of the data through pre-training,and combines the attention mechanism to discover where the mo-del pays more attention.In the second stage,the model uses geometric information to mine boundary features,and combines the attention weight obtained in the first stage to fuse the boundary features,so as to supplement minority classes.Experimental results on long tail CIFAR10,CIFAR100 and KDD Cup99 datasets show that the proposed feature fusion framework combining attention mechanism and geometric information can effectively improve the classification performance of imbalanced data,and can effectively improve the classification performance for different types of data,including image data and structured data. |
| first_indexed | 2024-04-09T17:32:12Z |
| format | Article |
| id | doaj.art-2b7642b92e3a4a28b986dc33ed16eeba |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:32:12Z |
| publishDate | 2022-05-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-2b7642b92e3a4a28b986dc33ed16eeba2023-04-18T02:35:57ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-05-0149512913410.11896/jsjkx.210300180Feature Fusion Framework Combining Attention Mechanism and Geometric InformationDONG Qi-da, WANG Zhe, WU Song-yang01 School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China ;2 The Third Research Institute of Ministry of Public Security,Shanghai 201204,ChinaThe imbalanced problem is common in the real world,and the highly-skewed distribution of imbalanced data seriously affects the performance of the model.In general,the imbalanced data affects the model performance from two aspects.On the one hand,the imbalance in sample size leads to more updates of parameters in majority classes,which leads to the model biased to majority classes.On the other hand,the sample size of minority classes is too small,and the diversity is insufficient,which leads to the insufficient representation ability of the model.To solve these problems,this paper proposes a feature fusion framework combining attention mechanism and geometric information.Specifically,in the first stage,the model learns the semantic information and discriminative information of the data through pre-training,and combines the attention mechanism to discover where the mo-del pays more attention.In the second stage,the model uses geometric information to mine boundary features,and combines the attention weight obtained in the first stage to fuse the boundary features,so as to supplement minority classes.Experimental results on long tail CIFAR10,CIFAR100 and KDD Cup99 datasets show that the proposed feature fusion framework combining attention mechanism and geometric information can effectively improve the classification performance of imbalanced data,and can effectively improve the classification performance for different types of data,including image data and structured data.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-5-129.pdfimbalanced data|feature fusion|deep learning|attention mechanism|geometric information |
| spellingShingle | DONG Qi-da, WANG Zhe, WU Song-yang Feature Fusion Framework Combining Attention Mechanism and Geometric Information Jisuanji kexue imbalanced data|feature fusion|deep learning|attention mechanism|geometric information |
| title | Feature Fusion Framework Combining Attention Mechanism and Geometric Information |
| title_full | Feature Fusion Framework Combining Attention Mechanism and Geometric Information |
| title_fullStr | Feature Fusion Framework Combining Attention Mechanism and Geometric Information |
| title_full_unstemmed | Feature Fusion Framework Combining Attention Mechanism and Geometric Information |
| title_short | Feature Fusion Framework Combining Attention Mechanism and Geometric Information |
| title_sort | feature fusion framework combining attention mechanism and geometric information |
| topic | imbalanced data|feature fusion|deep learning|attention mechanism|geometric information |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-5-129.pdf |
| work_keys_str_mv | AT dongqidawangzhewusongyang featurefusionframeworkcombiningattentionmechanismandgeometricinformation |