FeTT：通过特征变换调优实现持续类别增量学习
FeTT: Continual Class Incremental Learning via Feature Transformation Tuning
AI总结：
针对持续微调中的灾难性遗忘与特征通道抑制问题，本文提出非参数的FeTT特征变换调优模型，并结合多PTM扩展集成，在CL基准上验证了性能提升。
摘要：
持续学习（CL）旨在将深度模型从静态、封闭的环境扩展到动态、复杂的场景，使系统能够持续获取新类别的新知识，同时不遗忘先前已学到的知识。近期的CL模型已逐渐转向使用预训练模型（PTM），并采用参数高效微调（PEFT）策略。然而，由于缺少先前任务的数据，持续微调仍面临灾难性遗忘这一严峻挑战。此外，“先微调后冻结”机制还会因特征通道抑制以及首个CL任务中训练数据不足而受到性能限制。为此，本文提出特征变换调优（FeTT）模型，以非参数方式对所有任务的骨干网络特征进行微调；该方法不仅独立于CL训练数据运行，还能平滑特征通道，防止过度抑制。随后，将不同PTM与FeTT模型相结合的扩展集成策略进一步促进了性能提升。我们还从类别边缘分布差异和特征通道的角度，进一步阐述了对“先微调后冻结”范式及FeTT模型的讨论。在CL基准上进行的大量实验验证了所提方法的有效性。
英文摘要：
Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned knowledge. Recent CL models have gradually shifted towards the utilization of pre-trained models (PTMs) with parameter-efficient fine-tuning (PEFT) strategies. However, continual fine-tuning still presents a serious challenge of catastrophic forgetting due to the absence of previous task data. Additionally, the fine-tune-then-frozen mechanism suffers from performance limitations due to feature channels suppression and insufficient training data in the first CL task. To this end, this paper proposes feature transformation tuning (FeTT) model to non-parametrically fine-tune backbone features across all tasks, which not only operates independently of CL training data but also smooths feature channels to prevent excessive suppression. Then, the extended ensemble strategy incorporating different PTMs with FeTT model facilitates further performance improvement. We further elaborate on the discussions of the fine-tune-then-frozen paradigm and the FeTT model from the perspectives of discrepancy in class marginal distributions and feature channels. Extensive experiments on CL benchmarks validate the effectiveness of our proposed method.
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。
