Small sample image classification method based on interval supervision contrast loss

Abstract

The invention relates to the technical field of small sample image classification, in particular to a small sample image classification method based on interval supervised contrast loss, which comprises the following steps of: pre-training a model on a base class data set by utilizing a novel interval supervised contrast loss function, fixing parameters in an encoder in the pre-training model, extracting features from the support image samples in the new-class data set and training an SVM classifier; and finally, performing classification decision on the query samples by using the SVM. The interval supervision contrast loss function establishes a mathematical model for the contrast relationship between the base class samples instead of only paying attention to the class to which the base class samples belong, and the pre-trained backbone network has better mobility. The supervised contrast loss function in the invention can further reduce the distance of intra-class data and increase the inter-class distance by increasing the interval parameter, thereby further improving the classification performance.

Description

technical field [0001] The invention relates to the technical field of small sample image classification, in particular to a small sample image classification method based on interval supervision contrast loss. Background technique [0002] In recent years, deep learning has made major breakthroughs in several artificial intelligence fields such as computer vision, speech recognition, natural language processing, and autonomous driving. However, the powerful learning ability of deep convolutional neural networks completely relies on a large amount of hand-labeled data. Its big data-driven characteristics severely limit the application of deep learning technology in many practical situations. Because the cost of accurately labeling a large amount of data is very huge, and sometimes it is impossible to complete, such as medical data of rare diseases, image data of rare species, etc. In this context, scholars actively carry out research on the subject of small sample image cl...

AI Technical Summary

Problems solved by technology

Usually, such methods use the cross-entropy loss function to pre-train on the entire base class data set, and pay more attention to the category to which the base class samples belong, which seriously affects its transferability in the new class image domain.

Images