A Comparison of Deep Learning Classification Methods on Small-scale Image Data set: from Converlutional Neural Networks to Visual Transformers

Peng Zhao, Chen Li, Md Mamunur Rahaman, Hechen Yang, Tao jiang, Marcin Grzegorzek

In recent years, deep learning has made brilliant achievements in image classification. However, image classification of small datasets is still not obtained good research results. This article first briefly explains the application and characteristics of convolutional neural networks and visual transformers. Meanwhile, the influence of small data set on classification and the solution are introduced. Then a series of experiments are carried out on the small datasets by using various models, and the problems of some models in the experiments are discussed. Through the comparison of experimental results, the recommended deep learning model is given according to the model application environment. Finally, we give directions for future work.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment