RanPAC：用于持续学习的随机投影与预训练模型
RanPAC: Random Projections and Pre-trained Models for Continual Learning
AI总结：
本文提出RanPAC方法，通过在预训练模型特征后注入冻结的随机投影层并结合去相关的类原型累积，在不更新参数、不使用回放记忆的情况下有效缓解持续学习中的灾难性遗忘，在多个类别增量基准上显著降低错误率。
摘要：
持续学习（CL）旨在让模型在非平稳数据流中增量式地学习不同任务（例如分类），同时不遗忘旧任务。大多数持续学习研究聚焦于在从零开始学习的范式下解决灾难性遗忘问题。然而，随着基础模型的重要性日益提升，配备有信息丰富表示的预训练模型已经可以用于各种下游需求。已有若干基于预训练模型的持续学习方法被探索，这些方法要么直接利用预先提取的特征（这使得弥合分布差距变得困难），要么引入适配器（这可能仍会遭受遗忘）。在本文中，我们提出了一种简洁而有效的基于预训练模型的持续学习方法。鉴于遗忘发生在参数更新过程中，我们考虑了一种替代方案，即利用无需训练的随机投影器和类原型累积，从而绕开遗忘问题。具体而言，我们在预训练模型的特征表示与输出头之间注入一个带有非线性激活的冻结随机投影层，该层以扩展的维度捕捉特征之间的交互，为基于类原型的持续学习提供更强的线性可分性。我们还证明了在使用预训练表示时，对类原型进行去相关以减小分布差异的重要性。这些技术在类别增量持续学习和域增量持续学习中都证明是有效的，并且规避了遗忘问题。与先前应用于预训练ViT-B/16模型的方法相比，我们在七个类别增量基准上将最终错误率降低了20%至62%，尽管没有使用任何回放记忆。我们得出结论：预训练模型在简单、有效且快速的持续学习方面的全部潜力迄今尚未被充分挖掘。代码位于github.com/RanPAC/RanPAC。
英文摘要：
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch paradigm. However, with the increasing prominence of foundation models, pre-trained models equipped with informative representations have become available for various downstream requirements. Several CL methods based on pre-trained models have been explored, either utilizing pre-extracted features directly (which makes bridging distribution gaps challenging) or incorporating adaptors (which may be subject to forgetting). In this paper, we propose a concise and effective approach for CL with pre-trained models. Given that forgetting occurs during parameter updating, we contemplate an alternative approach that exploits training-free random projectors and class-prototype accumulation, which thus bypasses the issue. Specifically, we inject a frozen Random Projection layer with nonlinear activation between the pre-trained model's feature representations and output head, which captures interactions between features with expanded dimensionality, providing enhanced linear separability for class-prototype-based CL. We also demonstrate the importance of decorrelating the class-prototypes to reduce the distribution disparity when using pre-trained representations. These techniques prove to be effective and circumvent the problem of forgetting for both class- and domain-incremental continual learning. Compared to previous methods applied to pre-trained ViT-B/16 models, we reduce final error rates by between 20% and 62% on seven class-incremental benchmarks, despite not using any rehearsal memory. We conclude that the full potential of pre-trained models for simple, effective, and fast CL has not hitherto been fully tapped. Code is at github.com/RanPAC/RanPAC.
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。
