Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
This addresses the problem of model adaptation over diverse domains for AI systems in real-world scenarios, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles catastrophic forgetting in domain incremental learning by proposing DARE, a method that gradually adapts representations to new tasks while integrating task-specific boundaries, achieving reduced representation drift and maintained performance on previous tasks across multiple benchmarks.
Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation drift, which refers to the phenomenon of learned representations undergoing changes as the model adapts to new tasks, can help alleviate catastrophic forgetting. In this study, we propose a novel DIL method named DARE, featuring a three-stage training process: Divergence, Adaptation, and REfinement. This process gradually adapts the representations associated with new tasks into the feature space spanned by samples from previous tasks, simultaneously integrating task-specific decision boundaries. Additionally, we introduce a novel strategy for buffer sampling and demonstrate the effectiveness of our proposed method, combined with this sampling strategy, in reducing representation drift within the feature encoder. This contribution effectively alleviates catastrophic forgetting across multiple DIL benchmarks. Furthermore, our approach prevents sudden representation drift at task boundaries, resulting in a well-calibrated DIL model that maintains the performance on previous tasks.