类别增量学习中的概率阻尼与级联门控分类器
Class incremental learning with probability dampening and cascaded gated classifier
AI总结：
本文提出边际阻尼正则化与级联缩放门控分类器，通过软约束和知识蒸馏保留旧知识，以辅助缩放函数调整旧预测，在多个基准上优于基线方法。
摘要：
人类能够获取新知识并将所学知识迁移到不同领域，且遗忘程度较小。这种能力被称为持续学习，但在神经网络中实现却颇具挑战性，因为学习新任务时，网络会遗忘过去已学任务的知识。这种遗忘可以通过回放过去任务中存储的样本来缓解，但对于长任务序列，可能需要较大的内存容量；此外，这可能导致对已保存样本的过拟合。在本文中，我们提出了一种新颖的正则化方法和一种新颖的增量分类器，分别称为“边际阻尼”和“级联缩放分类器”。前者结合了软约束和知识蒸馏方法，以保留过去学到的知识，同时允许模型有效学习新模式。后者是一种门控增量分类器，通过辅助缩放函数修改模型输出，帮助模型在不直接干扰过去预测的情况下调整旧预测。我们通过实验证明，我们的方法在多个基准上相对于公认的基线方法表现良好，并且我们还研究了所提出方法的每个组成部分，以及这些组件的组合如何影响最终结果。
英文摘要：
Humans are capable of acquiring new knowledge and transferring learned knowledge into different domains, incurring a small forgetting. The same ability, called Continual Learning, is challenging to achieve when operating with neural networks due to the forgetting affecting past learned tasks when learning new ones. This forgetting can be mitigated by replaying stored samples from past tasks, but a large memory size may be needed for long sequences of tasks; moreover, this could lead to overfitting on saved samples. In this paper, we propose a novel regularisation approach and a novel incremental classifier called, respectively, Margin Dampening and Cascaded Scaling Classifier. The first combines a soft constraint and a knowledge distillation approach to preserve past learned knowledge while allowing the model to learn new patterns effectively. The latter is a gated incremental classifier, helping the model modify past predictions without directly interfering with them. This is achieved by modifying the output of the model with auxiliary scaling functions. We empirically show that our approach performs well on multiple benchmarks against well-established baselines, and we also study each component of our proposal and how the combinations of such components affect the final results.
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。
