PANDA -- 无示例持续学习中的补丁与分布感知增强
PANDA -- Patch And Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning
AI总结：
PANDA通过补丁与分布感知增强方法，解决无示例持续学习中的任务间不平衡问题，提升学习效果和泛化能力。
摘要：
无示例持续学习（EFCL）限制了先前任务数据的存储，并极易发生灾难性遗忘。尽管预训练模型（PTMs）越来越多地被用于EFCL，但现有方法往往忽视了现实世界数据分布的固有不平衡性。我们发现，现实世界的数据流通常表现出双重不平衡，即数据集层面的分布结合了单个任务内的极端或反向偏斜，从而在任务内和任务间产生差异，阻碍了有效学习和泛化。为了解决这些挑战，我们提出了PANDA，一种补丁与分布感知增强框架，能够无缝集成到现有的基于PTM的EFCL方法中。PANDA通过使用CLIP编码器识别代表性区域并将它们移植到每个任务中的频繁类样本中，来增强低频率类。此外，PANDA还集成了自适应平衡策略，利用先前任务分布来平滑任务间不平衡，减少任务间平均样本间的总体差距，从而在冻结PTMs的情况下实现更公平的学习。广泛的实验和消融研究证明了PANDA在与现有PTM-based CL方法结合时的能力，提高了准确性和减少了灾难性遗忘。
英文摘要：
Exemplar-Free Continual Learning (EFCL) restricts the storage of previous task data and is highly susceptible to catastrophic forgetting. While pre-trained models (PTMs) are increasingly leveraged for EFCL, existing methods often overlook the inherent imbalance of real-world data distributions. We discovered that real-world data streams commonly exhibit dual-level imbalances, dataset-level distributions combined with extreme or reversed skews within individual tasks, creating both intra-task and inter-task disparities that hinder effective learning and generalization. To address these challenges, we propose PANDA, a Patch-and-Distribution-Aware Augmentation framework that integrates seamlessly with existing PTM-based EFCL methods. PANDA amplifies low-frequency classes by using a CLIP encoder to identify representative regions and transplanting those into frequent-class samples within each task. Furthermore, PANDA incorporates an adaptive balancing strategy that leverages prior task distributions to smooth inter-task imbalances, reducing the overall gap between average samples across tasks and enabling fairer learning with frozen PTMs. Extensive experiments and ablation studies demonstrate PANDA's capability to work with existing PTM-based CL methods, improving accuracy and reducing catastrophic forgetting.
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。
