EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module
In this research, inspired by the principles of biological visual attention mechanisms and swarm intelligence found in nature, we present an Enhanced Self-Correlation Attention and Multi-Branch Joint Module Network (EMNet), a novel model for few-shot image classification. Few-shot image classificati...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/1/16 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588966876938240 |
|---|---|
| author | Fufang Li Weixiang Zhang Yi Shang |
| author_facet | Fufang Li Weixiang Zhang Yi Shang |
| author_sort | Fufang Li |
| collection | DOAJ |
| description | In this research, inspired by the principles of biological visual attention mechanisms and swarm intelligence found in nature, we present an Enhanced Self-Correlation Attention and Multi-Branch Joint Module Network (EMNet), a novel model for few-shot image classification. Few-shot image classification aims to address the problem of image classification when data are limited. Traditional models require a large amount of labeled data for training, while few-shot learning trains models using only a small number of samples (just a few samples per class) to recognize new categories. EMNet shows its potential for bio-inspired algorithms in optimizing feature extraction and enhancing generalization capabilities. It features two key modules: Enhanced Self-Correlated Attention (ESCA) and Multi-Branch Joint Module (MBJ Module). EMNet tackles two main challenges in few-shot learning: how to make an effective important feature extraction and enhancement in images, and improving generalization to new categories. The ESCA module boosts the precision in extracting crucial local features, enhancing classification accuracy. The MBJ module focuses on shared features across images, emphasizing similarities within classes and subtle differences between them. This enhances model adaptability and generalization to new categories. Experimental results show that our model performs better than existing models in one-shot and five-shot tasks on mini-ImageNet, CUB-200, and CIFAR-FS datasets, which proves the proposed model to be an efficient end-to-end solution for few-shot image classification. In the five-way one-shot and five-way five-shot experiments on the CUB-200-2011 dataset, EMNet achieved classification accuracies that were 1.27 and 0.54 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the miniImageNet dataset, EMNet’s classification accuracies were 0.02 and 0.48 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the CIFAR-FS dataset, EMNet’s classification accuracies were 0.19 and 0.18 percentage points higher than those of RENet. |
| format | Article |
| id | doaj-art-47b53ab746ff48948112ab983ab6d00a |
| institution | Kabale University |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-47b53ab746ff48948112ab983ab6d00a2025-01-24T13:24:36ZengMDPI AGBiomimetics2313-76732025-01-011011610.3390/biomimetics10010016EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint ModuleFufang Li0Weixiang Zhang1Yi Shang2School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, ChinaIn this research, inspired by the principles of biological visual attention mechanisms and swarm intelligence found in nature, we present an Enhanced Self-Correlation Attention and Multi-Branch Joint Module Network (EMNet), a novel model for few-shot image classification. Few-shot image classification aims to address the problem of image classification when data are limited. Traditional models require a large amount of labeled data for training, while few-shot learning trains models using only a small number of samples (just a few samples per class) to recognize new categories. EMNet shows its potential for bio-inspired algorithms in optimizing feature extraction and enhancing generalization capabilities. It features two key modules: Enhanced Self-Correlated Attention (ESCA) and Multi-Branch Joint Module (MBJ Module). EMNet tackles two main challenges in few-shot learning: how to make an effective important feature extraction and enhancement in images, and improving generalization to new categories. The ESCA module boosts the precision in extracting crucial local features, enhancing classification accuracy. The MBJ module focuses on shared features across images, emphasizing similarities within classes and subtle differences between them. This enhances model adaptability and generalization to new categories. Experimental results show that our model performs better than existing models in one-shot and five-shot tasks on mini-ImageNet, CUB-200, and CIFAR-FS datasets, which proves the proposed model to be an efficient end-to-end solution for few-shot image classification. In the five-way one-shot and five-way five-shot experiments on the CUB-200-2011 dataset, EMNet achieved classification accuracies that were 1.27 and 0.54 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the miniImageNet dataset, EMNet’s classification accuracies were 0.02 and 0.48 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the CIFAR-FS dataset, EMNet’s classification accuracies were 0.19 and 0.18 percentage points higher than those of RENet.https://www.mdpi.com/2313-7673/10/1/16few-shot image classificationfew-shot learningenhanced self-correlated attentionmulti-branch joint module |
| spellingShingle | Fufang Li Weixiang Zhang Yi Shang EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module Biomimetics few-shot image classification few-shot learning enhanced self-correlated attention multi-branch joint module |
| title | EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module |
| title_full | EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module |
| title_fullStr | EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module |
| title_full_unstemmed | EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module |
| title_short | EMNet: A Novel Few-Shot Image Classification Model with Enhanced Self-Correlation Attention and Multi-Branch Joint Module |
| title_sort | emnet a novel few shot image classification model with enhanced self correlation attention and multi branch joint module |
| topic | few-shot image classification few-shot learning enhanced self-correlated attention multi-branch joint module |
| url | https://www.mdpi.com/2313-7673/10/1/16 |
| work_keys_str_mv | AT fufangli emnetanovelfewshotimageclassificationmodelwithenhancedselfcorrelationattentionandmultibranchjointmodule AT weixiangzhang emnetanovelfewshotimageclassificationmodelwithenhancedselfcorrelationattentionandmultibranchjointmodule AT yishang emnetanovelfewshotimageclassificationmodelwithenhancedselfcorrelationattentionandmultibranchjointmodule |