arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2109.09150cs.LGcs.CV
收藏

自监督表示的泛化性研究

A Study of the Generalizability of Self-Supervised Representations

University of Nebraska-Lincoln(内布拉斯加大学林肯分校)

Atharva Tendle, Mohammad Rashedul Hasan

摘要:

自监督学习(SSL)的最新进展使得从未标记的数据中学习可推广的视觉表示成为可能。在预训练的SSL表示上微调的深度学习模型的性能与在最先进的监督学习(SL)表示上微调的模型相当。尽管SSL取得了进展,但其普遍性尚未得到广泛研究。在本文中,我们通过对迁移学习分类任务进行基于域的研究,对预训练的SSL和SL表示的泛化能力进行了更深入的分析。这些表示是从ImageNet源数据中学习的,然后使用两种类型的目标数据集进行微调:与源数据集相似,与源数据集显著不同。我们研究的SSL和SL为基础的模型,通过其预测精度以及预测置信度的泛化能力。除此之外,我们还分析了这些模型的最终卷积层的属性,以了解它们如何推理数据的语义身份。我们表明,SSL表示是更普遍的SL表示相比。我们解释的SSL表示的普遍性,通过调查其不变性,这是优于SL表示中观察到的。

英文摘要:

Recent advancements in self-supervised learning (SSL) made it possible to learn generalizable visual representations from unlabeled data. The performance of Deep Learning models fine-tuned on pretrained SSL representations is on par with models fine-tuned on the state-of-the-art supervised learning (SL) representations. Irrespective of the progress made in SSL, its generalizability has not been studied extensively. In this article, we perform a deeper analysis of the generalizability of pretrained SSL and SL representations by conducting a domain-based study for transfer learning classification tasks. The representations are learned from the ImageNet source data, which are then fine-tuned using two types of target datasets: similar to the source dataset, and significantly different from the source dataset. We study generalizability of the SSL and SL-based models via their prediction accuracy as well as prediction confidence. In addition to this, we analyze the attribution of the final convolutional layer of these models to understand how they reason about the semantic identity of the data. We show that the SSL representations are more generalizable as compared to the SL representations. We explain the generalizability of the SSL representations by investigating its invariance property, which is shown to be better than that observed in the SL representations.

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。

↑