Document worth reading: “Deep Learning for Fine-Grained Image Analysis: A Survey”

Computer imaginative and prescient (CV) is the tactic of using machines to understand and analyze imagery, which is an integral division of artificial intelligence. Among assorted evaluation areas of CV, fine-grained image analysis (FGIA) is a longstanding and primary disadvantage, and has flip into ubiquitous in quite a few real-world functions. The technique of FGIA targets analyzing seen objects from subordinate lessons, eg, species of birds or fashions of automobiles. The small inter-class variations and the large intra-class variations introduced on by the fine-grained nature makes it a troublesome disadvantage. During the booming of deep learning, newest years have witnessed excellent progress of FGIA using deep learning methods. In this paper, we aim to supply a survey on newest advances of deep learning based totally FGIA methods in a scientific method. Specifically, we handle the current analysis of FGIA methods into three major lessons: fine-grained image recognition, fine-grained image retrieval and fine-grained image know-how. In addition, we moreover cowl one other essential issues with FGIA, much like publicly accessible benchmark datasets and its related space explicit functions. Finally, we conclude this survey by highlighting a lot of directions and open points which need be further explored by the neighborhood ultimately. Deep Learning for Fine-Grained Image Analysis: A Survey