Description
Contrastive Multiview Coding (CMC) is a self-supervised learning approach, based on CPC, that learns representations that capture information shared between multiple sensory views. The core idea is to set an anchor view and the sample positive and negative data points from the other view and maximise agreement between positive pairs in learning from two views. Contrastive learning is used to build the embedding.
Papers Using This Method
Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition2022-05-20CSI: Contrastive Data Stratification for Interaction Prediction and its Application to Compound-Protein Interaction Prediction2021-11-18Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction2021-10-28InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training2020-07-15Contrastive Multiview Coding2019-06-13