Abstract:
Fine-grained visual classification is challenging due to subtle inter-class differences and strong visual similarity among categories. We propose RelFG-Net, a relational fine-grained framework that integrates graph-based reasoning with convolutional feature learning to explicitly model inter-class relationships. During training, dynamic class prototypes are constructed and refined through a sparsified class-relation graph using graph convolution layers, enabling structured message passing among similar categories. Experiments on CUB-200-2011, FGVC-Aircraft, and Stanford Cars demonstrate consistent improvements over DTRG. RelFG-Net achieves 2.35% Top-1 improvement on Aircraft, 1.34% on CUB, and 2.29% on Cars, while also improving Top-5 accuracy and F1-score across datasets. These results indicate that incorporating learnable relational reasoning over evolving class representations provides a stable and effective enhancement for fine-grained recognition.
Thesis Committee:
Internal Reader: Dr. Hamidreza Koohi
External Reader: Dr. Sudhir R. Paul
Advisor: Dr. Ziad Kobti
Location: 122 Essex Hall
