arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.05950q-bio.NC
收藏

人类和CNN中强大的翻译耐受性的案例。对Han等人的评论

A case for robust translation tolerance in humans and CNNs. A commentary on Han et al

Ryan Blything, Valerio Biscione, Jeffrey Bowers

摘要:

Han等人(2020)报告了一项行为实验,该实验评估了人类视觉系统在看不见的视网膜位置识别新图像的程度(作者称之为“内在平移不变性”),并开发了一种新的卷积神经网络模型(偏心依赖网络或ENN)来捕获行为结果的关键方面。在这里,我们表明,他们的行为数据分析使用不适当的基线条件,导致他们低估了内在的翻译不变性。当数据被正确解释时,它们显示出在某些条件下几乎完全的平移容限延伸到14°,与早期的工作一致(Bowers等人,2016)以及Blything等人最近的工作(出版中)。我们描述了一个更简单的模型,提供了一个更好的考虑平移不变性。

英文摘要:

Han et al. (2020) reported a behavioral experiment that assessed the extent to which the human visual system can identify novel images at unseen retinal locations (what the authors call "intrinsic translation invariance") and developed a novel convolutional neural network model (an Eccentricity Dependent Network or ENN) to capture key aspects of the behavioral results. Here we show that their analysis of behavioral data used inappropriate baseline conditions, leading them to underestimate intrinsic translation invariance. When the data are correctly interpreted they show near complete translation tolerance extending to 14° in some conditions, consistent with earlier work (Bowers et al., 2016) and more recent work Blything et al. (in press). We describe a simpler model that provides a better account of translation invariance.

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。

↑