We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from one task to the other. We show that the activation maps generated by the CNN trained on the old task can be calibrated using very few calibration parameters, to become relevant to the new task. Based on this, we calibrate the activation maps produced by each network layer using spatial and channel-wise calibration modules and train only these calibration parameters for each new task in order to perform lifelong learning. Our calibration modules introduce significantly less computation and parameters as compared to the approaches that dynamically expand the network. Our approach is immune to catastrophic forgetting since we store the task-adaptive calibration parameters, which contain all the task-specific knowledge and is exclusive to each task. Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods. We perform extensive experiments on multiple benchmark datasets (SVHN, CIFAR, ImageNet, and MS-Celeb), all of which show substantial improvements over state-of-the-art methods (e.g., a 29% absolute increase in accuracy on CIFAR-100 with 10 classes at a time).

Summary and Contributions: Update: My initial review noted two main issues with the paper: reliance on the initial model, and the use of task labels during the test phase. The author response addresses the first question, but misses the point on the second one. And this alone is not sufficient to strongly influence my overall rating. In my understanding, several previous methods, such as LwF, iCaRL highlighted in the author response, classify samples without the knowledge of which group of classes (i.e., old or new) they belong to. In other words, they only use a single framework that can identify samples from any of the old or the new classes, without additional information.

The paper proposes a continual learning approach for CNN models. This is achieved through spatial and channel-wise calibration modules, one for each new task. These calibration modules are introduced between each pair of consecutive layers in the original base model. The base model is learnt on the first task, and training data from the subsequent tasks is used to learn the calibration modules. Extensive experiments show the superiority of the proposed method in terms of accuracies, with minimal computation and storage overhead. It is important to emphasize that the proposed approach requires task labels in the test phase.

We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from one task to the other. We show that the activation maps generated by the CNN trained on the old task can be calibrated using very few calibration parameters, to become relevant to the new task. Based on this, we calibrate the activation maps produced by each network layer using spatial and channel-wise calibration modules and train only these calibration parameters for each new task in order to perform lifelong learning. Our calibration modules introduce significantly less computation and parameters as compared to the approaches that dynamically expand the network. Our approach is immune to catastrophic forgetting since we store the task-adaptive calibration parameters, which contain all the task-specific knowledge and is exclusive to each task.