arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.11523cs.CVcs.LGcs.NE
收藏

当前的自监督学习算法需要多少类似人类的视觉体验才能实现人类级别的物体识别?

How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?

New York University(纽约大学)

A. Emin Orhan

摘要:

本文解决了一个基本问题:我们目前的自我监督视觉表示学习算法相对于人类有多好?更具体地说,这些算法需要多少“类人”的自然视觉体验才能在复杂、现实的视觉对象识别任务(如ImageNet)中达到人类水平的性能?使用缩放实验,我们估计答案比人类寿命长几个数量级:通常在100万到10亿年的自然视觉体验(取决于所使用的算法)。我们在ImageNet衍生的鲁棒性基准测试中获得了更大的估计,以实现人类水平的性能。这些估计数的确切值对一些基本假设很敏感,但即使在最乐观的情况下,它们仍然比人类寿命大几个数量级。我们讨论了我们的估计和这些令人惊讶的结果的影响周围的主要警告。

英文摘要:

This paper addresses a fundamental question: how good are our current self-supervised visual representation learning algorithms relative to humans? More concretely, how much "human-like" natural visual experience would these algorithms need in order to reach human-level performance in a complex, realistic visual object recognition task such as ImageNet? Using a scaling experiment, here we estimate that the answer is several orders of magnitude longer than a human lifetime: typically on the order of a million to a billion years of natural visual experience (depending on the algorithm used). We obtain even larger estimates for achieving human-level performance in ImageNet-derived robustness benchmarks. The exact values of these estimates are sensitive to some underlying assumptions, however even in the most optimistic scenarios they remain orders of magnitude larger than a human lifetime. We discuss the main caveats surrounding our estimates and the implications of these surprising results.

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。

↑