AI RESEARCH
Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
arXiv CS.LG
•
In this work we introduce a novel approach to domain incremental learning, adapting models over time to evolving, non-stationary data. In contrast to other works, we do not attempt to avoid catastrophic forgetting, but rather allow it and exploit it. Our model combines a main task head with a self-supervised masked autoencoder (MAE) head.