arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01047cs.LGcs.AIcs.CV
收藏

在线持续学习中实时的评价:新的希望

Real-Time Evaluation in Online Continual Learning: A New Hope

King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学(KAUST));University of Oxford(牛津大学)

Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem

摘要:

当前对持续学习(CL)方法的评估通常假设对训练时间和计算没有约束。对于任何现实世界的设置来说,这都是一个不切实际的假设,这促使我们提出:对持续学习进行实用实时的【形】评估,其中流在揭示下一个预测数据之前不会等待模型完成训练。要做到这一点,我们评估当前CL方法的计算成本。我们在CLOC上进行了广泛的实验,CLOC是一个包含3900万个带有地理位置标签的时间戳图像的大规模数据集。我们表明,一个简单的基线优于国家的最先进的CL方法在此评估,质疑现有方法在现实环境中的适用性。此外,我们还探讨了文献中常用的各种CL组件,包括内存采样策略和正则化方法。我们发现,所有考虑的方法都无法与我们的简单基线竞争。这令人惊讶地表明,大多数现有的CL文献是针对特定类别的流,这是不实际的。我们希望,我们提供的评估将是第一步的范式转变,考虑在线持续学习方法的发展中的计算成本。

英文摘要:

Current evaluations of Continual Learning (CL) methods typically assume that there is no constraint on training time and computation. This is an unrealistic assumption for any real-world setting, which motivates us to propose: a practical real-time evaluation of continual learning, in which the stream does not wait for the model to complete training before revealing the next data for predictions. To do this, we evaluate current CL methods with respect to their computational costs. We conduct extensive experiments on CLOC, a large-scale dataset containing 39 million time-stamped images with geolocation labels. We show that a simple baseline outperforms state-of-the-art CL methods under this evaluation, questioning the applicability of existing methods in realistic settings. In addition, we explore various CL components commonly used in the literature, including memory sampling strategies and regularization approaches. We find that all considered methods fail to be competitive against our simple baseline. This surprisingly suggests that the majority of existing CL literature is tailored to a specific class of streams that is not practical. We hope that the evaluation we provide will be the first step towards a paradigm shift to consider the computational cost in the development of online continual learning methods.

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。

↑