Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature extractor, existing exemplar-free methods are typically evaluated in settings where the first task is significantly larger than subsequent tasks. Their performance drops drastically in more challenging settings starting with a smaller first task. To address this problem of feature drift estimation for exemplar-free methods, we propose to adversarially perturb the current samples such that their embeddings are close to the old class prototypes in the old model embedding space. We then estimate the drift in the embedding space from the old to the new model using the perturbed images and compensate the prototypes accordingly. We exploit the fact that adversarial samples are transferable from the old to the new feature space in a continual learning setting. The generation of these images is simple and computationally cheap. We demonstrate in our experiments that the proposed approach better tracks the movement of prototypes in embedding space and outperforms existing methods on several standard continual learning benchmarks as well as on fine-grained datasets. Code is available at https://github.com/dipamgoswami/ADC.

翻译：持续学习方法普遍存在灾难性遗忘问题，对于不存储先前任务示例的方法而言，这一问题尤为棘手。为减少特征提取器的潜在漂移，现有无示例方法通常在首个任务规模显著大于后续任务的设定下进行评估。当起始任务规模较小时，这些方法的性能在更具挑战性的设定下会急剧下降。为解决无示例方法的特征漂移估计问题，我们提出通过对当前样本进行对抗性扰动，使其嵌入向量在旧模型嵌入空间中接近旧类原型。随后，我们利用扰动图像估计从旧模型到新模型的嵌入空间漂移，并据此对原型进行补偿。该方法利用了持续学习设定中对抗样本可从旧特征空间迁移到新特征空间这一特性。此类图像的生成过程简单且计算成本低廉。实验表明，所提方法能更准确地追踪嵌入空间中原型的运动轨迹，在多个标准持续学习基准测试及细粒度数据集上均优于现有方法。代码发布于 https://github.com/dipamgoswami/ADC。