arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.14323cs.CVcs.LG
收藏

自我监督的预训练对视觉任务有多有用?

How Useful is Self-Supervised Pretraining for Visual Tasks?

Princeton University(普林斯顿大学)

Alejandro Newell, Jia Deng

摘要:

最近的进展在自我监督的视觉预训练方面取得了令人难以置信的进展。我们调查哪些因素可能发挥作用,这些预培训方法的实用性从业者。为此,我们在一系列综合的合成数据集和下游任务中评估了各种自监督算法。我们准备了一套合成数据,可以无休止地提供注释图像,并完全控制数据集的难度。我们的实验提供了洞察自我监督的效用如何随着可用标签数量的增长而变化,以及效用如何随着下游任务和训练数据的属性而变化。我们还发现,线性评价与微调性能无关。代码和数据可在\href{https://www.github.com/princeton-vl/selfstudy}{github.com/princeton-vl/selfstudy}上获得。

英文摘要:

Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. We prepare a suite of synthetic data that enables an endless supply of annotated images as well as full control over dataset difficulty. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows as well as how the utility changes as a function of the downstream task and the properties of the training data. We also find that linear evaluation does not correlate with finetuning performance. Code and data is available at \href{https://www.github.com/princeton-vl/selfstudy}{github.com/princeton-vl/selfstudy}.

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。

↑