IMAGE FEATURE SEPARATION USING CONTRASTIVE LEARNING
Keywords:
contrastive learning, image features, unsupervised learning, data representation, classification, computer vision.Abstract
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 data by 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 image analysis, especially in cases where large-scale annotated data is limited.
References
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. Proceedings of the 37th International Conference on Machine Learning, 1597–1607. 2. He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9729–9738. 3. Jaiswal, A., Babu, A. R., Zadeh, M. Z., Banerjee, D., & Makedon, F. (2021). A survey on contrastive self-supervised learning. Technologies, 9(1), 2. 4. Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., ... & Krishnan, D. (2020). Supervised contrastive learning. Advances in Neural Information Processing Systems, 33, 18661–18673. 5. Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images. University of Toronto Technical Report. 6. Coates, A., Ng, A., & Lee, H. (2011). An analysis of single-layer networks in unsupervised feature learning. Proceedings of the fourteenth international conference on artificial intelligence and statistics, 215–223. 7. Oord, A. v. d., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748. 8. Grill, J. B., Strub, F., Altché, F., Tallec, C., Richemond, P., Buchatskaya, E., ... & Valko, M. (2020). Bootstrap your own latent: A new approach to self-supervised learning. Advances in Neural Information Processing Systems, 33, 21271–21284. 9. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. Advances in Neural Information Processing Systems, 33, 9912–9924. 10. Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., & Isola, P. (2020). What makes for good views for contrastive learning? Advances in Neural Information Processing Systems, 33, 6827–6839.
