Contrastive Learning for Online Semi-Supervised General Continual Learning

07/12/2022

∙

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where every data added to memory is labeled using an oracle. Our approach outperforms existing semi-supervised methods when few labels are available, and obtain similar results to state-of-the-art supervised methods while using only 2.6 Split-CIFAR100.

READ FULL TEXT

Contrastive Learning for Online Semi-Supervised General Continual Learning

Learning to Predict Gradients for Semi-Supervised Continual Learning

Executive Function: A Contrastive Value Policy for Resampling and Relabeling Perceptions via Hindsight Summarization?

Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

A Distinct Unsupervised Reference Model From The Environment Helps Continual Learning

A soft nearest-neighbor framework for continual semi-supervised learning

Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning

Contrastive Learning for Online Semi-Supervised General Continual Learning

Related Research

Learning to Predict Gradients for Semi-Supervised Continual Learning

Executive Function: A Contrastive Value Policy for Resampling and Relabeling Perceptions via Hindsight Summarization?

Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

A Distinct Unsupervised Reference Model From The Environment Helps Continual Learning

A soft nearest-neighbor framework for continual semi-supervised learning

Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning