通过在线原型学习增强模型，实现高效抗遗忘的持续视觉学习。
Ancestral Mamba: Enhancing Selective Discriminant Space Model with Online Visual Prototype Learning for Efficient and Robust Discriminant Approach
- 引入动态原型更新与反馈机制，持续优化视觉表征
- 在CIFAR-10/100上准确率显著提升，遗忘率大幅降低
- 适合需要长期适应新视觉模式的动态图形任务
在计算机图形领域，从非平稳数据流中持续学习并适应新视觉模式、同时缓解灾难性遗忘至关重要。现有方法难以有效捕捉和表征不断演化的视觉概念，限制了其在动态图形任务中的应用。本文提出Ancestral Mamba，将在线原型学习融入选择性判别空间模型，实现高效且鲁棒的在线持续学习。核心包括：祖先原型自适应（APA），持续精炼并构建已有视觉原型；以及Mamba反馈（MF），针对挑战性视觉模式提供定向反馈。APA使模型基于历史知识应对新挑战，MF则聚焦困难类别，优化其表征。在面向图形任务的CIFAR-10和CIFAR-100数据集上的大量实验表明，Ancestral Mamba显著优于当前最优基线，在准确率和遗忘抑制方面均有明显提升。
原文摘要 · Abstract (English)
In the realm of computer graphics, the ability to learn continuously from non-stationary data streams while adapting to new visual patterns and mitigating catastrophic forgetting is of paramount importance. Existing approaches often struggle to capture and represent the essential characteristics of evolving visual concepts, hindering their applicability to dynamic graphics tasks. In this paper, we propose Ancestral Mamba, a novel approach that integrates online prototype learning into a selective discriminant space model for efficient and robust online continual learning. The key components of our approach include Ancestral Prototype Adaptation (APA), which continuously refines and builds upon learned visual prototypes, and Mamba Feedback (MF), which provides targeted feedback to adapt to challenging visual patterns. APA enables the model to continuously adapt its prototypes, building upon ancestral knowledge to tackle new challenges, while MF acts as a targeted feedback mechanism, focusing on challenging classes and refining their representations. Extensive experiments on graphics-oriented datasets, such as CIFAR-10 and CIFAR-100, demonstrate the superior performance of Ancestral Mamba compared to state-of-the-art baselines, achieving significant improvements in accuracy and forgetting mitigation.
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。