Encoders and Ensembles for Task-Free Continual Learning
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once). To obtain good performance under these constraints, while mitigating catastrophic forgetting, we exploit recent advances in contrastive, self-supervised learning, allowing us to use a pre-trained, general purpose image encoder whose weights can be frozen, which precludes forgetting. The pre-trained encoder also greatly simplifies the downstream task of classification, which we solve with an ensemble of very simple classifiers. Collectively, the ensemble exhibits much better performance than any individual classifier, an effect which is amplified through specialisation and competitive selection. We assess the performance of the encoders-and-ensembles architecture on standard continual learning benchmarks, where it outperforms prior state-of-the-art by a large margin on the hardest problems, as well as in less familiar settings where the data distribution changes gradually or the classes are presented one at a time.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningImage ClassificationSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Ensembles and Encoders for Task-Free Continual Learning
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each presented …
Continual LearningSelf-Supervised LearningContinual Learning Beyond a Single Model
A growing body of research in continual learning focuses on the catastrophic forgetting problem. While many attempts have been made to alleviate this problem, the majority of the methods assume a single model in the cont…
Continual LearningmodelClass Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay
This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs) and variational autoencoders (VAEs) to enable memory-efficient replay, eliminating the need to store raw data samp…
Continual LearningContinual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition
Continual learning for reinforcement learning agents remains a significant challenge, particularly in preserving and leveraging existing information without an external signal to indicate changes in tasks or environments…
Continual LearningSequential Learning and Catastrophic Forgetting in Differentiable Resistor Networks
Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in …
Continual Learning