提出SAMix方法，提升持续学习模型的准确性与预测可靠性。
SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
- 基于神经坍缩特性设计自适应混合策略，优化特征空间对齐
- 在多个数据集上超越现有方法，准确率与校准度同步提升
- 适合追求高可靠预测的持续学习应用，如医疗、自动驾驶
尽管多数持续学习方法聚焦于缓解遗忘和提升准确率，却常忽略网络校准这一关键问题。神经坍缩现象（即最后一层特征坍缩至类别均值）在持续学习中展现出优势，可减少特征与分类器之间的错位。然而，极少研究致力于改进持续学习模型的校准能力以实现更可靠的预测。本文提出一种新方法：通过引入球面自适应混合（SAMix），不仅增强模型校准性，还改善性能，降低过自信、缓解遗忘并提高准确率。SAMix是一种针对神经坍缩型方法设计的自适应混合策略，能根据特征空间在神经坍缩下的几何特性动态调整混合过程，从而实现更稳健的正则化与对齐。实验表明，SAMix显著提升性能，在多个持续学习基准上超越当前最优方法，并同时改善模型校准。该方法在跨任务准确率和预测可靠性方面均有提升，为构建鲁棒持续学习系统提供了有力支持。
原文摘要 · Abstract (English)
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where last-layer features collapse to their class means, has demonstrated advantages in continual learning by reducing feature-classifier misalignment. Few works aim to improve the calibration of continual models for more reliable predictions. Our work goes a step further by proposing a novel method that not only enhances calibration but also improves performance by reducing overconfidence, mitigating forgetting, and increasing accuracy. We introduce Sphere-Adaptive Mixup (SAMix), an adaptive mixup strategy tailored for neural collapse-based methods. SAMix adapts the mixing process to the geometric properties of feature spaces under neural collapse, ensuring more robust regularization and alignment. Experiments show that SAMix significantly boosts performance, surpassing SOTA methods in continual learning while also improving model calibration. SAMix enhances both across-task accuracy and the broader reliability of predictions, making it a promising advancement for robust continual learning systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。