任务新近性偏差的反击：在无样本类别增量学习中自适应协方差
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
AI总结：
本文针对无样本类别增量学习中协方差失配与维度坍缩导致的任务新近性偏差，提出 AdaGauss 逐任务自适应高斯协方差并加入反坍缩损失，在多种基准上达到最先进性能。
摘要：
无样本类别增量学习（EFCIL）解决的是在无法访问过去数据的情况下，按一系列任务训练模型的问题。现有最先进方法在特征提取器的隐空间中将类别表示为高斯分布，从而实现贝叶斯分类，或通过重放伪特征来训练分类器。然而，我们发现当特征提取器在增量任务上更新时，存在两个损害其有效性的关键问题。首先，它们没有考虑各类别的协方差矩阵会发生变化，并且必须在每个任务之后进行自适应调整。其次，它们容易受到训练期间发生的维度坍缩所导致的任务新近性偏差影响。在本工作中，我们提出 AdaGauss——一种新颖方法，可逐任务自适应协方差矩阵，并借助额外的反坍缩损失函数缓解任务新近性偏差。无论是从头开始训练，还是从预训练骨干网络开始，AdaGauss 都在常用 EFCIL 基准和数据集上取得了最先进结果。代码可在 https://github.com/grypesc/AdaGauss 获取。
英文摘要：
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.
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。
