Research on deep learning method for fine-grained image classification

Abstract

The public has long been interested in computer vision research projects on image classification. Over the past 20 years, fine-grained image classification (FGIC) has advanced quickly because of the ongoing development of deep neural network models. The FDIC is based on the traditional image classification and further identifies the subtle differences between subclasses within the same category. Deep learning-based image categorization techniques are separated into two groups in this article: FGIC based on intensely supervised learning and weakly supervised learning. Briefly, it introduces the algorithms included in each category. Additionally, this article lists the performance of several methods on the well-known CUB-200 dataset and gives typical fine-grained picture datasets. By comparing several algorithms' outputs, it is determined that weakly supervised learning has the advantages of lower cost and higher accuracy than intensely supervised learning. Finally, the paper proposes a summary and a discussion of fine-grained images' potential future development prospects.