无数据储备特征用于高效长时域冷启动持续学习
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
AI总结：
提出CIRCLE方法，使用固定的双向二维储备特征和流式线性判别分析头，无需重放、预训练或骨干网络反向传播，在长任务序列中显著优于现有冷启动无样本类增量学习方法。
摘要：
冷启动无样本类增量学习需要在不使用重放、外部预训练或大型初始任务的情况下学习不断增长的类别集合。现有的冷启动方法通常要么在整个数据流中训练骨干网络并补偿语义漂移，要么在第一个任务后冻结骨干网络，产生偏向初始类别的特征。这些选择也造成了计算上的矛盾：漂移补偿方法需要重复训练骨干网络，且随着任务时域增长更新成本越来越高，而冻结骨干网络的方法虽然廉价但在冷启动下表现较弱。我们研究了第三种选择：一个从未拟合图像数据的特征提取器。我们提出CIRCLE，一个基于固定的双向二维储备特征（从BiRC2D改编用于图像分类）和流式线性判别分析头的类增量分类器。CIRCLE将多个随机储备实例分组为特征集成，并独立SLDA头的softmax输出进行平均，从而在更丰富的随机特征和预测级集成之间产生可调的偏差-方差权衡。由于特征提取器固定且头支持流式闭式更新，CIRCLE无需重放、任务边界信息或骨干网络反向传播即可进行样本级训练。在CIFAR-100、TinyImageNet、ImageNet-Subset和ImageNet-1k上，CIRCLE在10-20任务划分中具有竞争力，并在50、100和500任务划分中大幅优于强CS-EFCIL基线，同时训练速度远快于基于训练骨干网络的漂移补偿方法。消融实验表明，BiRC2D风格提取器、SLDA头以及平衡的特征/预测集成各自对最终性能有贡献。
英文摘要：
Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task. Existing cold-start methods typically either train the backbone throughout the stream and compensate for semantic drift, or freeze a backbone after the first task, producing features biased toward the initial classes. These choices also create a computational tension: drift-compensation methods require repeated backbone training and increasingly expensive updates as the task horizon grows, while frozen-backbone methods are cheap but weak under cold start. We study a third option: a feature extractor that is never fit to image data at all. We propose CIRCLE, a class-incremental classifier built from fixed bidirectional two-dimensional reservoir features, adapted from BiRC2D for image classification, and streaming linear discriminant analysis heads. CIRCLE groups multiple random reservoir instantiations into feature ensembles and averages the softmax outputs of independent SLDA heads, yielding a tunable bias-variance tradeoff between richer random features and prediction-level ensembling. Because the feature extractor is fixed and the head admits streaming closed-form updates, CIRCLE performs sample-wise training without replay, task-boundary information, or backbone backpropagation. On CIFAR-100, TinyImageNet, ImageNet-Subset, and ImageNet-1k, CIRCLE is competitive at 10-20 task splits and substantially outperforms strong CS-EFCIL baselines at 50, 100, and 500 task splits, while training much faster than trained-backbone drift-compensation methods. Ablations show that the BiRC2D-style extractor, SLDA head, and balanced feature/prediction ensembling each contribute to the final performance.
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。
