FOSTER: Feature Boosting and Compression for Class-Incremental Learning
This addresses the problem of efficient and effective continual learning for deep neural networks, though it appears incremental as it builds on existing gradient boosting and distillation techniques.
The paper tackles catastrophic forgetting in class-incremental learning by proposing FOSTER, a two-stage method that dynamically expands modules to fit residuals and then compresses the model, achieving state-of-the-art performance on CIFAR-100 and ImageNet datasets.
The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this phenomenon, whereas most of them either fall into the stability-plasticity dilemma or take too much computation or storage overhead. Inspired by the gradient boosting algorithm to gradually fit the residuals between the target model and the previous ensemble model, we propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively. Specifically, we first dynamically expand new modules to fit the residuals between the target and the output of the original model. Next, we remove redundant parameters and feature dimensions through an effective distillation strategy to maintain the single backbone model. We validate our method FOSTER on CIFAR-100 and ImageNet-100/1000 under different settings. Experimental results show that our method achieves state-of-the-art performance. Code is available at: https://github.com/G-U-N/ECCV22-FOSTER.