基于特征的图注意力网络改进在线持续学习
Feature-based Graph Attention Networks Improve Online Continual Learning
AI总结：
针对图像分类在线持续学习中传统CNN和Transformer的局限，提出基于图注意力网络（GATs）的框架，结合分层特征图转图、增强全局池化及排练记忆复制技术，在多基准数据集上性能优于现有方法。
摘要：
图像分类的在线持续学习对于模型在适应新数据的同时保留先前学习任务的知识至关重要。这种能力对于应对涉及动态环境和不断变化的数据分布的现实世界挑战至关重要。传统方法主要采用卷积神经网络，其局限于将图像作为网格处理，且主要捕捉局部模式而非关系信息。尽管Transformer架构的出现提高了捕捉关系的能力，但这些模型通常需要显著更多的资源。在本文中，我们提出了一种基于图注意力网络（GATs）的新型在线持续学习框架，该框架能有效捕捉上下文关系，并通过学习的注意力权重动态更新任务特定表示。我们的方法利用预训练特征提取器，通过分层特征图将图像转换为图，以不同粒度表示信息。这些图随后由GAT处理，并结合增强的全局池化策略，以提高持续学习的分类性能。此外，我们提出了排练记忆复制技术，在维持记忆预算的同时改进先前任务的表示。在包括SVHN、CIFAR10、CIFAR100和MiniImageNet在内的基准数据集上的综合评估表明，我们的方法优于现有最先进方法。
英文摘要：
Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic environments and evolving data distributions. Traditional approaches predominantly employ Convolutional Neural Networks, which are limited to processing images as grids and primarily capture local patterns rather than relational information. Although the emergence of transformer architectures has improved the ability to capture relationships, these models often require significantly larger resources. In this paper, we present a novel online continual learning framework based on Graph Attention Networks (GATs), which effectively capture contextual relationships and dynamically update the task-specific representation via learned attention weights. Our approach utilizes a pre-trained feature extractor to convert images into graphs using hierarchical feature maps, representing information at varying levels of granularity. These graphs are then processed by a GAT and incorporate an enhanced global pooling strategy to improve classification performance for continual learning. In addition, we propose the rehearsal memory duplication technique that improves the representation of the previous tasks while maintaining the memory budget. Comprehensive evaluations on benchmark datasets, including SVHN, CIFAR10, CIFAR100, and MiniImageNet, demonstrate the superiority of our method compared to the state-of-the-art methods.
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。
