具有任务特定批量规范化和分布外检测的增量学习
Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection
AI总结：
本研究提出一种基于任务特定批量规范化和分布外检测的增量学习框架，有效提升模型在新任务中的可塑性与旧任务的稳定性。
摘要：
本研究聚焦于图像分类中的增量学习，探讨在无法访问旧数据时如何减少所有已学习知识的灾难性遗忘。挑战在于平衡可塑性（学习新知识）和稳定性（保留旧知识）。基于测试时任务标识符（task-ID）是否可用，增量学习被分为任务增量学习（TIL）和类增量学习（CIL）。TIL范式通常使用多个分类器头，根据任务-ID选择相应的头。由于CIL范式无法访问任务-ID，原本为TIL开发的方法需要显式预测任务-ID以弥补这一差距，并使其适应CIL范式。在本研究中，一种新颖的持续学习框架扩展了用于CIL的TIL方法，通过引入分布外检测来预测任务-ID。我们的框架利用任务特定的批量规范化（BN）和任务特定的分类头，有效调整每个任务的特征图分布，提高可塑性。相比卷积核，参数更少的任务特定BN有助于最小化参数增长，保持稳定性。基于多个任务特定的分类头，我们为每个头引入一个"未知"类。在训练时，其他任务的数据被映射到这个未知类。在推断时，通过选择分配给未知类概率最低的分类头来预测任务-ID。我们的方法在两个医学图像数据集和两个自然图像数据集上实现了最先进的性能。源代码可在https://github.com/z1968357787/mbn_ood_git_main获取。
英文摘要：
This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new knowledge) and stability (retaining old knowledge). Based on whether the task identifier (task-ID) is available during testing, incremental learning is divided into task incremental learning (TIL) and class incremental learning (CIL). The TIL paradigm often uses multiple classifier heads, selecting the corresponding head based on the task-ID. Since the CIL paradigm cannot access task-ID, methods originally developed for TIL require explicit task-ID prediction to bridge this gap and enable their adaptation to the CIL paradigm. {In this study, a novel continual learning framework extends the TIL method for CIL by introducing out-of-distribution detection for task-ID prediction. Our framework utilizes task-specific Batch Normalization (BN) and task-specific classification heads to effectively adjust feature map distributions for each task, enhancing plasticity. With far fewer parameters than convolutional kernels, task-specific BN helps minimize parameter growth, preserving stability. Based on multiple task-specific classification heads, we introduce an ``unknow'' class for each head. During training, data from other tasks are mapped to this unknown class. During inference, the task-ID is predicted by selecting the classification head with the lowest probability assigned to the unknown class. Our method achieves state-of-the-art performance on two medical image datasets and two natural image datasets. The source code is available at https://github.com/z1968357787/mbn_ood_git_main.
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。
