用邻近特征聚类提升持续学习性能，适应新类别变化。
FeNeC: Enhancing Continual Learning via Feature Clustering with Neighbor- or Logit-Based Classification
- 基于特征聚类与马氏距离，动态捕捉类内变化。
- 在任务身份未知场景下表现优异，部分任务超越现有方法。
- 适合长期学习新类别、数据分布漂移的场景。
深度学习模型持续学习能力对适应新数据类别和演化数据分布至关重要。近年来，许多方法在初始训练后冻结特征提取器，并基于主干网络生成的特征表示估计每类协方差矩阵和原型。在此范式下，我们提出FeNeC（特征邻域分类器）及其基于对数似然函数的变体FeNeC-Log。通过引入数据聚类，我们的方法能更充分捕捉类内可变性。利用马氏距离，模型通过最近邻或可训练的对数几率值对样本进行分类。该方法在特定情况下可退化为已有方法，但具备更强的灵活性以适应数据变化。我们验证了两种FeNeC变体在任务身份未知场景下表现良好，并在多个基准上取得当前最优结果。
原文摘要 · Abstract (English)
The ability of deep learning models to learn continuously is essential for adapting to new data categories and evolving data distributions. In recent years, approaches leveraging frozen feature extractors after an initial learning phase have been extensively studied. Many of these methods estimate per-class covariance matrices and prototypes based on backbone-derived feature representations. Within this paradigm, we introduce FeNeC (Feature Neighborhood Classifier) and FeNeC-Log, its variant based on the log-likelihood function. Our approach generalizes the existing concept by incorporating data clustering to capture greater intra-class variability. Utilizing the Mahalanobis distance, our models classify samples either through a nearest neighbor approach or trainable logit values assigned to consecutive classes. Our proposition may be reduced to the existing approaches in a special case while extending them with the ability of more flexible adaptation to data. We demonstrate that two FeNeC variants achieve competitive performance in scenarios where task identities are unknown and establish state-of-the-art results on several benchmarks.
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。