# Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams Source: [Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams]() Collection index: [llms.txt]() Data updated: 2026-06-02T05:00:12.522Z Authors: Jonathan Swinnen, Tinne Tuytelaars Published: 2026-05-29T10:17:09.000Z ## Abstract 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. We then learn domain-specific LoRA adapters during incremental training. Each adapter specializes to its domain, naturally inducing forgetting on other domains in both heads. At inference, we perform online test-time training on the self-supervised MAE head to identify which LoRAs best matches the current input, so the model can \`remember' the domain again. Our scheme is especially well-suited to real-world streaming data, such as video, where consecutive samples are highly correlated and domain shifts are gradual. We demonstrate our method on domain-incremental action recognition and semantic segmentation tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Segmentation on Domains Campus](): Semantic segmentation; Domains Campus; FAA: 45.8. - [Action Recognition on NTU-RGB+D 120](): Action Recognition; NTU RGB+D 120; FAA: 69.9. ## Original sources and implementation [Original paper]() [PDF]()