【作者单位】a National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China; b College of Computer Science, Sichuan University, Chengdu, China; c School of Information Science and Technology, Tibet University, Lhasa, China
【摘要】 Fine-grained visual categorization that aims to recognize objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation caused by, e.g., deformation, occlusion, illumi...
