Part-guided Relational Transformers for Fine-grained Visual Recognition

• Published in: IEEE transactions on image processing Vol. 30; p. 1
• Main Authors: Zhao, Yifan, Li, Jia, Chen, Xiaowu, Tian, Yonghong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Correlation; Costs; Embedding; Feature extraction; Fine-grained visual recognition; Modules; Natural language processing; Object recognition; Part discovery; Relationship; Semantics; Task analysis; Transformers; Visualization

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different subcategories still remains a challenge. In this paper, we propose to s...