Fine-Grained Object Recognition Using a Combination Model of Navigator–Teacher–Scrutinizer and Spinal Networks

Fine-grained object recognition aims to recognize objects with a large variety of intraclass and low variations between classes. To overcome this problem, using a simple model may hard to find more discriminative parts. Thus, we proposed a combination model of navigator–teacher–scrutinizer and spinal networks to improve accuracy. Employing two feature extractors, residual networks with 50 and 101 layers deep, and replacing the basic fully connected layer with spinal network outperform the baseline results on Stanford Cars, Fine-Grained Visual Classification of Aircraft, and 275 Bird Species datasets.