Performacnes comparison of CNN-based models for fine-grained image classification

Abstract

Fine-grained visual classification is regarded as a more refined classification that can identify specific types of objects. It has been widely used in commodity sales, vehicle recognition and person recognition, etc., and has played a great value in many fields. For example, it requires an algorithm to identify different species of birds or dogs to facilitate more practical applications. This task is difficult since the objects has similar appearance and there exist obvious intra-class variance and limited inter-class differences, where different kinds of birds could share very similar appearance. Deep learning techniques has been applied to image recognition, natural language processing, and many other fields. Several approaches tackling the fine-grained classification problem are proposed. To further demonstrate the different designs of these solutions, in this paper, fine-grained identification methods are compared and analyzed, among which WS-DAN achieves better results and it is preferred to be an effective method, which is expected to be more widely used in this field.