Single-Net Continual Learning with Progressive Segmented Training (PST)
This addresses the problem of efficient and accurate continual learning for dynamic systems like self-driving vehicles, though it is incremental as it builds on existing single-network approaches.
The paper tackles catastrophic forgetting in continual learning by proposing Progressive Segmented Training (PST), which uses a single network to separate parameters into frozen and saved groups, achieving state-of-the-art accuracy on CIFAR-10 and CIFAR-100 datasets with improved computational efficiency.
There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference. Different from previous approaches with dynamic structures, this work focuses on a single network and model segmentation to prevent catastrophic forgetting. Leveraging the redundant capacity of a single network, model parameters for each task are separated into two groups: one important group which is frozen to preserve current knowledge, and secondary group to be saved (not pruned) for a future learning. A fixed-size memory containing a small amount of previously seen data is further adopted to assist the training. Without additional regularization, the simple yet effective approach of PST successfully incorporates multiple tasks and achieves the state-of-the-art accuracy in the single-head evaluation on CIFAR-10 and CIFAR-100 datasets. Moreover, the segmented training significantly improves computation efficiency in continual learning.