DeepAI AI Chat
Log In Sign Up

Feature Extraction Framework based on Contrastive Learning with Adaptive Positive and Negative Samples

by   Hongjie Zhang, et al.
China Agricultural University

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.


page 1

page 2

page 3

page 4


A Unified Framework for Feature Extraction based on Contrastive Learning

Feature extraction is an efficient approach for alleviating the curse of...

Prototype-based interpretation of the functionality of neurons in winner-take-all neural networks

Prototype-based learning (PbL) using a winner-take-all (WTA) network bas...

Characterization of Covid-19 Dataset using Complex Networks and Image Processing

This paper aims to explore the structure of pattern behind covid-19 data...

Multi-view Feature Extraction based on Triple Contrastive Heads

Multi-view feature extraction is an efficient approach for alleviating t...

Contrasting the landscape of contrastive and non-contrastive learning

A lot of recent advances in unsupervised feature learning are based on d...

Multi-view Feature Extraction based on Dual Contrastive Head

Multi-view feature extraction is an efficient approach for alleviating t...

Real-centric Consistency Learning for Deepfake Detection

Most of previous deepfake detection researches bent their efforts to des...