Parameter-Efficient Augment Plugin for Class-Incremental Learning

Existing class-incremental learning (CIL) approaches based on replay or knowledge distillation are often constrained by forgetting or the stability-plasticity dilemma. Some expansion-based approaches could achieve higher accuracy. However, they always require significant parameter increases. In this paper, we propose a plugin extension paradigm termed the Deployment of extra LoRA Components (DLC) for non-pre-trained CILthis http URLtreat the feature extractor trained through replay or distillation as a base model with rich knowledge. For each task, we use Low-Rank Adaptation (LoRA) to inject task-specific residuals into the base model's deep layers. During inference, representations with task-specific residuals are aggregated to produce classification predictions. To mitigate interference from non-target LoRA plugins, we introduce a lightweight weighting unit. This unit learns to assign importance scores to different LoRA-tuned representations. Like downloadable contents in software, our method serves as a plug-and-play enhancement that efficiently extends the base methods. Remarkably, on the large-scale ImageNet-100, with merely 4 % of the parameters of a standard ResNet-18, our DLC model achieves a significant 8 % improvement in accuracy, demonstrating exceptional efficiency. Moreover, it could surpass state-of-the-art methods under the fixed memory budget.