Abstract

In fine-grained visual categorization (FGVC), there is a near-singular focus in pursuit of attaining state-of-the-art (SOTA) accuracy. This work carefully analyzes the performance of recent SOTA methods, quantitatively, but more importantly, qualitatively. We show that these models universally struggle with certain "hard" images, while also making complementary mistakes. We underscore the importance of such analysis, and demonstrate that combining complementary models can improve accuracy on the popular CUB-200 dataset by over 5%. In addition to detailed analysis and characterization of the errors made by these SOTA methods, we provide a clear set of recommended directions for future FGVC researchers.

Degree

MS

College and Department

Physical and Mathematical Sciences

Rights

https://lib.byu.edu/about/copyright/

Date Submitted

2020-07-29

Document Type

Thesis

Handle

http://hdl.lib.byu.edu/1877/etd11343

Keywords

computer vision, fgvc, deep learning

Language

english

Share

COinS