Few-shot Fine-grained Image Recognition Based on Discriminative Feature Enhancement
Few-shot fine-grained image recognition is a popular research topic in the field of deep learning.Its basic task is to identify images of subcategories under a super class while learning a limited number of samples.Thanks to the rapid development of convolutional neural networks,the accuracy of few-shot fine-grained image recognition has achieved remarkable results,but its performance is still limited by the high variance among images of the same subclass and the variability of discriminative features in different classification tasks.To address the above problems,we propose a few-shot fine-grained image recognition algorithm(DFENet)based on discriminative feature enhancement.DFENet is designed with a symmetric attention module to enhance intra-class visual consistency learning,thus reducing the influence of background and increasing the weight of feature representations shared among similar samples.In addition,DFENet introduces a discriminative feature enhancement module of channel dimension,and further mines discriminative features suitable for the current task by exploiting the channel relationships within similar samples and between samples of different classes in the support set to improve the recognition accuracy.Extensive experiments are conducted on three classical fine-grained datasets CUB-200-2011,Stanford Dogs,and Stanford Cars.It is showed that the proposed method all achieves competitive results.
国家科技期刊平台
NSTL
万方数据
维普
