Continual Learning (CL) focuses on maximizing the predictive performance of a
model across a non-stationary stream of data. Unfortunately, CL models tend to
forget previous knowledge, thus often underperforming when compared with an
offline model trained jointly on the entire data stream. Given that any CL
model will eventually make mistakes, it is of crucial importance to build
calibrated CL models: models that can reliably tell their confidence when
making a prediction. Model calibration is an active research topic in machine
learning, yet to be properly investigated in CL. We provide the first empirical
study of the behavior of calibration approaches in CL, showing that CL
strategies do not inherently learn calibrated models. To mitigate this issue,
we design a continual calibration approach that improves the performance of
post-processing calibration methods over a wide range of different benchmarks
and CL strategies. CL does not necessarily need perfect predictive models, but
rather it can benefit from reliable predictive models. We believe our study on
continual calibration represents a first step towards this direction.

持续学习聚焦于在非平稳数据流上最大化模型的预测性能。本文通过第一次对持续学习中校准方法行为的实证研究，展示了持续学习策略并不能自然地学习到校准模型，并设计了一种持续校准方法，该方法通过后处理校准方法在不同基准和持续学习策略范围内提升性能。

连续学习模型的校准

Calibration of Continual Learning Models

The Long-Tailed Recognition (LTR) problem emerges in the context of learning
from highly imbalanced datasets, in which the number of samples among different
classes is heavily skewed. LTR methods aim to accurately learn a dataset
comprising both a larger Head set and a smaller Tail set. We propose a theorem
where under the assumption of strong convexity of the loss function, the
weights of a learner trained on the full dataset are within an upper bound of
the weights of the same learner trained strictly on the Head. Next, we assert
that by treating the learning of the Head and Tail as two separate and
sequential steps, Continual Learning (CL) methods can effectively update the
weights of the learner to learn the Tail without forgetting the Head. First, we
validate our theoretical findings with various experiments on the toy MNIST-LT
dataset. We then evaluate the efficacy of several CL strategies on multiple
imbalanced variations of two standard LTR benchmarks (CIFAR100-LT and
CIFAR10-LT), and show that standard CL methods achieve strong performance gains
in comparison to baselines and approach solutions that have been tailor-made
for LTR. We also assess the applicability of CL techniques on real-world data
by exploring CL on the naturally imbalanced Caltech256 dataset and demonstrate
its superiority over state-of-the-art classifiers. Our work not only unifies
LTR and CL but also paves the way for leveraging advances in CL methods to
tackle the LTR challenge more effectively.

本文提出了解决长尾识别问题的两个重要方法：理论公式证明将全数据集训练的权重控制在同样训练头部数据的权重上限范围内；将头部和尾部的学习视为分开的顺序步骤，使用 Continual Learning 方法来有效地更新学习者的权重。作者在 CIFAR100-LT，CIFAR10-LT 和 Caltech-256 等数据集上执行的实验结果表明，Continual Learning 方法可以比 LTR 专用解决方案更有效地解决长尾识别问题。