Continually Learning Self-Supervised Representations with Projected Functional Regularization
This addresses the challenge of continual learning for self-supervised representations, which is incremental as it adapts existing methods to avoid forgetting in non-IID data scenarios.
The paper tackles the problem of enabling self-supervised learning methods to acquire new knowledge incrementally in continual learning regimes without replay mechanisms, showing that naive functional regularization limits performance and proposing Projected Functional Regularization to prevent forgetting while maintaining plasticity, resulting in competitive performance across multiple datasets.
Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally -- they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay mechanism. We show that naive functional regularization, also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional Regularization in which a separate temporal projection network ensures that the newly learned feature space preserves information of the previous one, while at the same time allowing for the learning of new features. This prevents forgetting while maintaining the plasticity of the learner. Comparison with other incremental learning approaches applied to self-supervision demonstrates that our method obtains competitive performance in different scenarios and on multiple datasets.