通过球面专家混合提升持续学习中的特征分离能力
Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
- 在超球面上用预定义的ETF分类器实现特征重排
- 引入Mixture of Experts动态扩展ETF，提升跨任务特征区分度
- 在11个数据集上比最强基线高2%准确率，尤其适合细粒度识别
持续学习使模型能在保留旧知识的同时学习新任务。但引入新任务常导致任务间特征纠缠，削弱模型对新领域数据的区分能力。本文提出一种名为Fresh-CL的方法：在超球面上利用预定义且固定的单纯形等角紧框架（ETF）分类器，提升任务内与任务间的特征分离。然而，新任务带来的ETF投影变化会破坏旧任务的结构化特征表示，导致性能下降。为此，我们提出基于专家混合（MoE）的ETF动态扩展机制，实现自适应地投影到多样化子空间，增强特征表达。在11个数据集上的实验表明，相比最强基线，准确率提升2%，尤其在细粒度数据集上表现更优，验证了ETF与MoE结合在持续学习中提升特征区分的有效性。
原文摘要 · Abstract (English)
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.
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。