As neural networks are increasingly being applied to real-world applications,
mechanisms to address distributional shift and sequential task learning without
forgetting are critical. Methods incorporating network expansion have shown
promise by naturally adding model capacity for learning new tasks while
simultaneously avoiding catastrophic forgetting. However, the growth in the
number of additional parameters of many of these types of methods can be
computationally expensive at larger scales, at times prohibitively so. Instead,
we propose a simple task-specific feature map transformation strategy for
continual learning, which we call Efficient Feature Transformations (EFTs).
These EFTs provide powerful flexibility for learning new tasks, achieved with
minimal parameters added to the base architecture. We further propose a feature
distance maximization strategy, which significantly improves task prediction in
class incremental settings, without needing expensive generative models. We
demonstrate the efficacy and efficiency of our method with an extensive set of
experiments in discriminative (CIFAR-100 and ImageNet-1K) and generative (LSUN,
CUB-200, Cats) sequences of tasks. Even with low single-digit parameter growth
rates, EFTs can outperform many other continual learning methods in a wide
range of settings.

本文提出了一种称为 EFTs 的简单的任务特定特征映射转换策略，具有强大的灵活性，利用最小的参数增加了基本体系结构，使其在大规模场景下实用；我们还提出了一种特征距离最大化策略来完成类增量设置中的任务预测。通过在较广泛的一系列任务序列中的实验，包括区分性任务和生成任务，证明了该方法的实效性和效率。