剪枝适应模块：一种简单却强大的连续基础模型基线
Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
AI总结：
本文提出剪枝适应模块（PAM），通过冻结大部分预训练ResNet参数，利用稀疏任务特定层实现可扩展的连续学习，显著降低持续学习成本并减少遗忘。
摘要：
持续学习文献已迅速从传统类增量学习（CIL）技术转向基于基础模型（FM）的CIL方法，但缺乏对这些新方法与强大轻量级卷积基线比较的清晰理解。为填补这一方法学差距，我们引入剪枝适应模块（PAM），一种简单有效的技术，通过冻结大部分预训练ResNet参数，利用稀疏任务特定层实现可扩展的持续学习。PAM在可训练参数和总参数上分别减少约5倍和6倍，显著降低持续更新成本。在多样化的基准测试中，PAM一致缓解了灾难性遗忘并优于最先进的FM-based CIL方法。我们的发现将PAM定位为一种强大且透明的基线，有助于弥合传统与FM-based CIL之间的差距，指导未来研究以更准确评估持续学习的真正进展。代码可在：https://github.com/ElifCerenGokYildirim/PAM找到。
英文摘要：
The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong, lightweight convolutional baselines. This abrupt transition has created a substantial methodological gap, making it difficult to assess whether recent FM-based CIL progress reflects genuine advances or merely the absence of rigorous baselines. To address this gap, we introduce Pruned Adaptation Modules (PAM), a simple yet effective method that freezes the vast majority of the pre-trained ResNet while enabling scalable continual adaptation through sparse task-specific layers. PAM yields up to a ~5x reduction in trainable parameters and a ~6x reduction in total parameters, significantly reducing the cost of continual updates. Across diverse benchmarks, PAM consistently mitigates catastrophic forgetting and outperforms state-of-the-art FM-based CIL approaches. Our findings position PAM as a strong and transparent baseline that helps bridge the gap between traditional and FM-based CIL, guiding future research for a more accurate assessment of true progress in continual adaptation. The code can be found at: https://github.com/ElifCerenGokYildirim/PAM.
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。
