面向少样本类增量学习的连续知识保持分解与自适应层选择
Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
AI总结：
针对少样本类增量学习中的稳定性-可塑性平衡问题，提出CKPD-FSCIL框架，通过连续知识保持分解和自适应层选择利用预训练权重冗余容量，实现零推理开销的高效适配。
摘要：
少样本类增量学习（FSCIL）面临一个关键挑战：在保留先前知识与获取新类别之间取得平衡。现有方法要么冻结骨干网络以防止灾难性遗忘，从而牺牲可塑性；要么添加新模块，导致高昂成本。这些方法将预训练模型视为黑箱，忽视了两个利用其内部容量的关键机会：重用层内冗余的表示空间，以及根据各层对遗忘的敏感性进行选择性适配。我们提出CKPD-FSCIL，一个统一框架，释放预训练权重中未被充分利用的容量，在零推理开销下实现优越的稳定性-可塑性平衡。我们的设计整合了两个连续适配机制：在权重层面，连续知识保持分解机制利用特征协方差将每个权重矩阵分解为一个保护先前知识的冻结子空间和一个用于新任务的可学习冗余子空间。在层级层面，连续自适应层选择机制利用适配器敏感性比率自动选择具有最高冗余容量和最低遗忘风险的层进行适配。通过仅针对安全、高潜力的子空间和层，CKPD-FSCIL实现了高效适配。每个会话结束后，学习到的适配器被合并回原始权重中，确保推理过程中零额外参数或FLOPs。在多个FSCIL基准上的大量实验表明，我们的方法在适应性和知识保持方面均一致优于最先进方法。代码可在https://github.com/xiaojieli0903/CKPD-FSCIL获取。
英文摘要：
Few-Shot Class-Incremental Learning (FSCIL) faces a critical challenge: balancing the retention of prior knowledge with the acquisition of new classes. Existing methods either freeze the backbone to prevent catastrophic forgetting, sacrificing plasticity, or add new modules, incurring high costs. These approaches treat pretrained models as black boxes, overlooking two key opportunities to exploit their internal capacity: reusing redundant representational space within layers and selectively adapting layers based on their sensitivity to forgetting. We propose CKPD-FSCIL, a unified framework that unlocks the underutilized capacity of pretrained weights, achieving a superior stability-plasticity balance with zero inference overhead. Our design integrates two continuously adapting mechanisms: At the weight level, a Continuous Knowledge-Preserving Decomposition mechanism uses feature covariance to split each weight matrix into a frozen subspace that safeguards prior knowledge and a learnable, redundant subspace for new tasks. At the layer level, a Continuous Adaptive Layer Selection mechanism leverages an Adapter Sensitivity Ratio to automatically select layers with the highest redundant capacity and lowest forgetting risk for adaptation. By targeting only safe, high-potential subspaces and layers, CKPD-FSCIL enables efficient adaptation. After each session, the learned adapters are merged back into the original weights, ensuring zero additional parameters or FLOPs during inference. Extensive experiments on multiple FSCIL benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in both adaptability and knowledge retention. The code is available at https://github.com/xiaojieli0903/CKPD-FSCIL.
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。
