Fresh-CL：持续学习中通过超球面上专家实现的特征重对齐
Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
AI总结：
针对持续学习中新任务引入导致的特征纠缠问题，提出结合超球面单纯形ETF与动态MoE扩展的Fresh-CL方法，11个数据集实验显示较最强基线准确率提升2%，有效增强特征区分度。
摘要：
持续学习使模型能够在保留已有知识的同时学习并适应新任务。然而，引入新任务自然会导致跨任务的特征纠缠，限制模型区分新领域数据的能力。在本研究中，我们提出了一种名为持续学习中通过超球面上专家实现特征重对齐（Feature Realignment through Experts on hyperSpHere in Continual Learning，Fresh-CL）的方法。通过利用超球面上预定义且固定的单纯形等角紧框架（simplex equiangular tight frame，ETF）分类器，我们的模型提升了任务内和任务间的特征分离度。但向单纯形ETF的投影会随新任务发生偏移，破坏先前任务的结构化特征表示并导致性能下降。因此，我们提出通过混合专家（mixture of experts，MoE）对ETF进行动态扩展，实现向多样子空间的自适应投影，以增强特征表示。在11个数据集上的实验表明，与最强基线相比，该方法的准确率提升了2%，在细粒度数据集上表现尤为突出，证实了结合ETF与MoE在持续学习场景中提升特征区分度的有效性。
英文摘要：
Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish between new domain data. In this work, we propose a method called Feature Realignment through Experts on hyperSpHere in Continual Learning (Fresh-CL). By leveraging predefined and fixed simplex equiangular tight frame (ETF) classifiers on a hypersphere, our model improves feature separation both intra and inter tasks. However, the projection to a simplex ETF shifts with new tasks, disrupting structured feature representation of previous tasks and degrading performance. Therefore, we propose a dynamic extension of ETF through mixture of experts, enabling adaptive projections onto diverse subspaces to enhance feature representation. Experiments on 11 datasets demonstrate a 2% improvement in accuracy compared to the strongest baseline, particularly in fine-grained datasets, confirming the efficacy of combining ETF and MoE to improve feature distinction in continual learning scenarios.
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。
