提出AdaGauss，解决无样本增量学习中协方差未更新和任务新近性偏差问题。
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
- 动态调整类别协方差矩阵以适应新任务
- 引入反坍缩损失缓解维度坍缩导致的旧类遗忘
- 适用于从零训练或预训练模型开始的场景
无样本增量学习（EFCIL）在不访问历史数据的情况下逐步训练模型。现有先进方法将类别表示为特征提取器隐空间中的高斯分布，支持贝叶斯分类或通过重放伪特征训练分类器。然而，我们发现当特征提取器在增量任务上更新时，两类关键问题损害其效果：一是类别协方差矩阵随任务变化，但现有方法未动态调整；二是训练中出现维度坍缩，引发任务新近性偏差。为此，本文提出AdaGauss，通过任务间自适应协方差并引入额外的抗坍缩损失函数，有效缓解该偏差。在多个主流EFCIL基准和数据集上，无论从零训练或使用预训练主干网络，均取得当前最优性能。代码已开源：https://github.com/grypesc/AdaGauss。
原文摘要 · Abstract (English)
Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature extractor's latent space, enabling Bayes classification or training the classifier by replaying pseudo features. However, we identify two critical issues that compromise their efficacy when the feature extractor is updated on incremental tasks. First, they do not consider that classes' covariance matrices change and must be adapted after each task. Second, they are susceptible to a task-recency bias caused by dimensionality collapse occurring during training. In this work, we propose AdaGauss -- a novel method that adapts covariance matrices from task to task and mitigates the task-recency bias owing to the additional anti-collapse loss function. AdaGauss yields state-of-the-art results on popular EFCIL benchmarks and datasets when training from scratch or starting from a pre-trained backbone. The code is available at: https://github.com/grypesc/AdaGauss.
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。