Research and Implementation of Autonomous Learning Platform for Image Classification

The image classification task aims to automatically classify image content based on machine learning methods. This task is a basic task in the field of computer vision, which has broad application prospects and great research value. At present, in the case of large-scale corpus annotation, mainstream image classification algorithms based on deep learning have been able to obtain better classification results. In order to achieve the above goals, this paper has carried out the following work. This paper studies two mainstream pre-training models in the field of image classification: one is the CNN network based on residual learning; the other is the Vision Transformer model based on Transformer. And according to the performance comparison of each model in four data sets: MNIST, CIFAR-10, CIFAR-100 and ImageNet under different parameters, the optimal model is selected as the background training model of the system. The experimental results show that the Transformer-based model Vision Transformer has better performance and can be used as the back-end training model of the autonomous learning platform.