Image classification method, classification network training method and related products

The invention relates to the technical field of computer vision, and particularly provides an image classification method, a classification network training method and a related product. The classification network training method comprises the following steps: training a to-be-trained classification network based on sample data to obtain a trained classification network, wherein the sample data comprises new sample data belonging to a new category and historical sample data belonging to an old category; obtaining the center feature of each category in the trained classification network according to the features of the sample data; determining a preset number of target sample data from the sample data belonging to each category according to the center feature of each category; and updating the historical sample data based on the target sample data corresponding to each category. According to the training method, the training time of the classification network is shortened, and the training speed is increased.