Image classification method and system based on incremental learning

Abstract

The embodiment of the invention provides an image classification method and system based on incremental learning, and a computer medium, and the method comprises the steps: selecting old category dataof an old classification model and new incremental data, and constructing an incremental learning data set; constructing an incremental learning new classification model; inputting an incremental learning data set to the incremental learning new classification model, and performing incremental learning training under the constraint of an incremental learning loss function to obtain a trained incremental learning new classification model; and inputting a to-be-classified image to the trained incremental learning new classification model, and carrying out image classification to obtain an imageclassification result. According to the method, learning is carried out on the basis of the old category data together with the new category data, the similarity of the mapping vectors of the old category can be kept consistent in the incremental learning process under the constraint of the incremental learning loss function, and then the classification performance of the test data of the old category is kept while the information of the new category is learned.

Description

technical field [0001] The present application belongs to the technical field of image classification, and in particular relates to an image classification method and system based on incremental learning. Background technique [0002] Incremental learning is an important research topic in machine learning. The goal of incremental learning is to continuously learn new knowledge through new data without forgetting the learned knowledge. Many real-world applications of computer vision require models to be capable of incremental learning. For example, a face recognition system should support adding new face data, and should not reduce its learning performance on old face data. For another example, the product identification system in an unmanned supermarket should continuously learn the knowledge of newly added products while maintaining the recognition accuracy of the original products. Compared with incremental learning and full learning (that is, the model is retrained on a...

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes an image classification method and system based on incremental learning, aiming to solve the problem of catastrophic forgetting in the existing incremental learning. After the model learns the information of the new category, the performance of the old category test data is large The problem of reduced magnitude

Images