对抗性伪回放用于无示例的类增量学习
Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning
AI总结：
本文提出对抗性伪回放方法，通过扰动新任务图像生成伪回放样本，以解决无示例类增量学习中的稳定性与塑性矛盾，提升冷启动设置下的性能。
摘要：
无示例的类增量学习（EFCIL）旨在在学习新类别时保留先前任务获得的旧知识，而无需存储先前图像，这是由于存储限制或隐私问题。在EFCIL中，塑性与稳定性之间的矛盾，即学习新任务与灾难性遗忘之间的平衡，是一个重大挑战，主要由于早期任务的图像不可用。在本文中，我们引入了对抗性伪回放（APR），一种通过对抗性攻击扰动新任务图像以在线合成伪回放图像的方法，而无需存储任何回放样本。在新任务训练过程中，对抗性攻击是在增强的旧类均质原型作为目标上对新任务图像进行的，所生成的图像用于知识蒸馏以防止语义漂移。此外，我们通过在伪回放样本上学习转移矩阵来校准协方差矩阵，以在每次任务后补偿语义漂移。我们的方法实现了稳定性与塑性的平衡，在标准EFCIL基准的具有挑战性的冷启动设置上达到了最先进的性能。
英文摘要：
Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the plasticity-stability dilemma, learning new tasks versus catastrophic forgetting, is a significant challenge, primarily due to the unavailability of images from earlier tasks. In this paper, we introduce adversarial pseudo-replay (APR), a method that perturbs the images of the new task with adversarial attack, to synthesize the pseudo-replay images online without storing any replay samples. During the new task training, the adversarial attack is conducted on the new task images with augmented old class mean prototypes as targets, and the resulting images are used for knowledge distillation to prevent semantic drift. Moreover, we calibrate the covariance matrices to compensate for the semantic drift after each task, by learning a transfer matrix on the pseudo-replay samples. Our method reconciles stability and plasticity, achieving state-of-the-art on challenging cold-start settings of the standard EFCIL benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
