arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.12855q-bio.NC
收藏

人类视觉系统和CNN都可以在极端位移之后支持强大的在线翻译容忍度

The human visual system and CNNs can both support robust online translation tolerance following extreme displacements

Ryan Blything, Valerio Biscione, Ivan I. Vankov, Casimir J. H. Ludwig, Jeffrey S. Bowers

摘要:

视觉平移容忍度是指我们在广泛的不同视网膜位置上识别物体的能力。虽然平移可能是视觉系统需要处理的最简单的空间变换,但人类视觉系统在多大程度上可以识别以前看不见的位置的物体尚不清楚,一些研究报告在10°以上几乎完全不变性,而其他研究报告在4°视角下零不变性。类似地,关于视觉计算模型中的翻译容忍度以及人类和模型性能之间的匹配程度也存在混淆。在这里,我们报告了一系列眼动跟踪研究(总N=70),证明在一个视网膜位置训练的新物体可以在平移高达18°后以高准确率识别。我们还表明,当预训练以对一系列位置上的另一组刺激进行分类时,或者当添加全局平均池化(GAP)层以产生更大的感受野时,标准深度卷积网络(DCNN)支持我们的发现。我们的研究结果为人类视觉理论提供了强有力的约束,并有助于解释以前报道的CNN不一致的发现。

英文摘要:

Visual translation tolerance refers to our capacity to recognize objects over a wide range of different retinal locations. Although translation is perhaps the simplest spatial transform that the visual system needs to cope with, the extent to which the human visual system can identify objects at previously unseen locations is unclear, with some studies reporting near complete invariance over 10° and other reporting zero invariance at 4° of visual angle. Similarly, there is confusion regarding the extent of translation tolerance in computational models of vision, as well as the degree of match between human and model performance. Here we report a series of eye-tracking studies (total N=70) demonstrating that novel objects trained at one retinal location can be recognized at high accuracy rates following translations up to 18°. We also show that standard deep convolutional networks (DCNNs) support our findings when pretrained to classify another set of stimuli across a range of locations, or when a Global Average Pooling (GAP) layer is added to produce larger receptive fields. Our findings provide a strong constraint for theories of human vision and help explain inconsistent findings previously reported with CNNs.

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。

↑