Channel-Wise Attention-Enhanced Feature Mutual Reconstruction for Few-Shot Fine-Grained Image Classification
Open Access
- 19 January 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (2) , 377
Abstract
Fine-grained image classification is faced with the challenge of significant intra-class differences and subtle similarities between classes, with a limited number of labelled data. Previous few-shot learning approaches, however, often fail to recognize these discriminative details, such as a bird’s eyes and beak. In this paper, we proposed a channel-wise attention-enhanced feature mutual reconstruction mechanism that helps to alleviate these problems for fine-grained image classification. This mechanism first employed a channel-wise attention module (CAM) to learn the channel weights for both the support and query features. We utilized channel-wise self-attention to assign greater importance to object-relevant channels. This helps the model to focus on subtle yet discriminative details, which is essential to the classification process. Then, we introduce a feature mutual reconstruction module (FMRM) to reconstruct features. The support features are reconstructed by a support-weight-enhanced feature map to reduce the intra-class variations, and query features are reconstructed by a query-weight-enhanced feature map to increase inter-class variations. The results of classification depend on the similarity between reconstructed features and enhanced features. We evaluated the performance based on four fine-grained image datasets when Conv-4 and Resnet-12 were used. The experimental results showed that our method outperforms previous few-shot fine-grained classification methods. This proves that our method can improve fine-grained image classification performance and simultaneously balance both the inter-class and intra-class variations.Keywords
This publication has 30 references indexed in Scilit:
- Few-Shot Fine-Grained Image Classification via Multi-Frequency Neighborhood and Double-Cross ModulationIEEE Transactions on Multimedia, 2024
- nnFormer: Volumetric Medical Image Segmentation via a 3D TransformerIEEE Transactions on Image Processing, 2023
- From Instance to Metric Calibration: A Unified Framework for Open-World Few-Shot LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Knowledge-Guided Semantic Transfer Network for Few-Shot Image RecognitionIEEE Transactions on Neural Networks and Learning Systems, 2023
- Boosting Few-Shot Fine-Grained Recognition With Background Suppression and Foreground AlignmentIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Learning attention-guided pyramidal features for few-shot fine-grained recognitionPattern Recognition, 2022
- Fine-Grained Image Analysis With Deep Learning: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic ReviewIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
- Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image ClassificationIEEE Transactions on Multimedia, 2020
- Deep Residual Learning for Image Recognition2016