Wang Jiale, Lu Jin, Yang Junpo, Wang Meijia, Zhang Weichuan
School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an 710000, China.
Sensors (Basel). 2024 Dec 3;24(23):7737. doi: 10.3390/s24237737.
Few-shot fine-grained image classification (FSFGIC) aims to classify subspecies with similar appearances under conditions of very limited data. In this paper, we observe an interesting phenomenon: different types of image data augmentation techniques have varying effects on the performance of FSFGIC methods. This indicates that there may be biases in the features extracted from the input images. The bias of the acquired feature may cause deviation in the calculation of similarity, which is particularly detrimental to FSFGIC tasks characterized by low inter-class variation and high intra-class variation, thus affecting the classification accuracy. To address the problems mentioned, we propose an unbiased feature estimation network. The designed network has the capability to significantly optimize the quality of the obtained feature representations and effectively reduce the feature bias from input images. Furthermore, our proposed architecture can be easily integrated into any contextual training mechanism. Extensive experiments on the FSFGIC tasks demonstrate the effectiveness of the proposed algorithm, showing a notable improvement in classification accuracy.
少样本细粒度图像分类（FSFGIC）旨在在数据非常有限的条件下对外观相似的亚种进行分类。在本文中，我们观察到一个有趣的现象：不同类型的图像数据增强技术对FSFGIC方法的性能有不同的影响。这表明从输入图像中提取的特征可能存在偏差。所获取特征的偏差可能会导致相似度计算出现偏差，这对于具有低类间差异和高类内差异特征的FSFGIC任务尤其不利，从而影响分类准确率。为了解决上述问题，我们提出了一种无偏特征估计网络。所设计的网络能够显著优化所获得特征表示的质量，并有效减少来自输入图像的特征偏差。此外，我们提出的架构可以很容易地集成到任何上下文训练机制中。在FSFGIC任务上进行的大量实验证明了所提算法的有效性，分类准确率有显著提高。
