Feature Extraction Framework based on Contrastive Learning with Adaptive Positive and Negative Samples
This work addresses feature extraction for unsupervised, supervised, and semi-supervised single-view data, but it appears incremental as it builds on existing contrastive learning techniques.
The study tackled the problem of feature extraction by proposing a contrastive learning framework with adaptive positive and negative samples, achieving strong advantages over traditional methods and other contrastive learning approaches in numerical experiments.
In this study, we propose a feature extraction framework based on contrastive learning with adaptive positive and negative samples (CL-FEFA) that is suitable for unsupervised, supervised, and semi-supervised single-view feature extraction. CL-FEFA constructs adaptively the positive and negative samples from the results of feature extraction, which makes it more appropriate and accurate. Thereafter, the discriminative features are re extracted to according to InfoNCE loss based on previous positive and negative samples, which will make the intra-class samples more compact and the inter-class samples more dispersed. At the same time, using the potential structure information of subspace samples to dynamically construct positive and negative samples can make our framework more robust to noisy data. Furthermore, CL-FEFA considers the mutual information between positive samples, that is, similar samples in potential structures, which provides theoretical support for its advantages in feature extraction. The final numerical experiments prove that the proposed framework has a strong advantage over the traditional feature extraction methods and contrastive learning methods.