GradMix: 基于梯度的选取混合法用于类别增量学习中的鲁棒数据增强
GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental Learning
AI总结：
GradMix是一种基于梯度的选取混合方法，用于减少类别增量学习中的灾难性遗忘，通过混合有益类对样本以提升模型性能。
摘要：
在持续学习的背景下，获取新知识的同时保持原有知识是一个重大挑战。现有方法通常使用经验回放技术，存储少量先前任务数据进行训练。在经验回放方法中，数据增强已成为一种有前景的策略，通过混合有限的先前任务数据和充足的当前任务数据来进一步提高模型性能。然而，我们理论和实证分析表明，使用随机样本对混合样本进行训练可能会损害先前任务的知识，并导致更大的灾难性遗忘。我们随后提出GradMix，一种专门设计用于减轻类别增量学习中灾难性遗忘的鲁棒数据增强方法。GradMix通过基于类别的标准进行梯度基于的选取混合，仅混合对有益的类对样本，而不混合有害的类对样本，以减少灾难性遗忘。我们在各种真实数据集上的实验表明，GradMix在准确率上优于数据增强基线，通过最小化先前知识的遗忘来实现。
英文摘要：
In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data for training. In experience replay approaches, data augmentation has emerged as a promising strategy to further improve the model performance by mixing limited previous task data with sufficient current task data. However, we theoretically and empirically analyze that training with mixed samples from random sample pairs may harm the knowledge of previous tasks and cause greater catastrophic forgetting. We then propose GradMix, a robust data augmentation method specifically designed for mitigating catastrophic forgetting in class-incremental learning. GradMix performs gradient-based selective mixup using a class-based criterion that mixes only samples from helpful class pairs and not from detrimental class pairs for reducing catastrophic forgetting. Our experiments on various real datasets show that GradMix outperforms data augmentation baselines in accuracy by minimizing the forgetting of previous knowledge.
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。
