IMAGE FEATURE SEPARATION USING CONTRASTIVE LEARNING

This article studies the problem of image feature separation using the contrastive learning method. The main goal of the study is to evaluate the effectiveness of contrastive learning, an unsupervised approach, in extracting independent and robust features from image data. The problem is that traditional supervised learning methods depend on a large set of defined data, which requires a lot of resources and time. Contrastive learning, on the other hand, learns the self-representation of databy comparing pairs of similar and dissimilar images, which makes it possible to work with less information. In the study, a contrastive model was built on simulated data and its performance was evaluated. The results showed that the contrastive learning method provided approximately 8-9% higher accuracy in the task of image classification than traditional autoencoding networks. In conclusion, it can be said that contrastive learning is an effective and resource-saving approach for imageanalysis, especially in cases where large-scale annotated data is limited.