Over the past decade, deep learning has become the core one of the most powerful and robust algorithms in the artificial intelligence and machine learning field (Zhang et al., 2022). The Deep learning can be implemented with good performance in tasks of acoustics, images, natural language processing, etc. Here will discuss particular on the image field. In image research self there found many tasks that can do it, one of them was image classification or image recognition. For image classification, we discuss famous algorithms that suitable to classify images from the fine-grained dataset. Some fine-grained datasets are Caltech-UCSD Birds (CUB-200-2011), Stanford Cars, and Fine-Grained Visual Classification (FGVC) Aircraft. And the deep learning algorithm that has been giving the satisfying performance was NTS-Net (see Figure 1). NTS-Net stands for Navigator-Teacher-Scrutinizer Network (Yang et al., 2018).

Referensi:

Yang, Z., Luo, T., Wang, D., Hu, Z., Gao, J., & Wang, L. (2018). Learning to Navigate for Fine-grained Classification. arXiv. https://doi.org/10.48550/ARXIV.1809.00287

Zhang, Z., Cui, P., & Zhu, W. (2022). Deep Learning on Graphs: A Survey. IEEE Transactions on Knowledge and Data Engineering, 34(1), 249–270. https://doi.org/10.1109/TKDE.2020.2981333