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 2301.07455q-bio.NC
收藏

预测编码深度神经网络中的不一致虚幻运动

Inconsistent illusory motion in predictive coding deep neural networks

O. R. Kirubeswaran, Katherine R. Storrs

摘要:

为什么我们会在一些静态图像中感知到虚幻的运动?已经提出了几个帐户的基础上,眼球运动,响应延迟到不同的图像元素,或图像模式和运动能量检测器之间的相互作用。最近,据报道,基于预测编码原理的递归深度神经网络(DNN)PredNet可以重现“旋转蛇”错觉,这表明预测编码在错觉运动中的作用。我们复制了这一发现,然后使用一系列的“在硅片上的心理物理学”实验,以检查是否PredNet的行为与人类观察者一致的简化变体的错觉刺激。我们还通过探测网络中的内部单元来测量对旋转蛇模式的各个元素的响应延迟。预训练的PredNet模型预测了旋转蛇刺激的所有子组件的错觉运动,与人类观察者一致。然而,我们没有发现简单的反应延迟的内部单位,发现在生理数据。PredNet模型的梯度运动检测是基于对比度,而不是亮度,因为它是在人类的感知。最后,我们在10个相同的PredNet上测试了错觉的鲁棒性,这些PredNet是在相同的视频数据上训练的;我们发现网络再现错觉和预测错觉简化变体的运动的能力存在很大差异。此外,与人类观察者不同的是,没有一个网络预测到模式的灰度变体的虚幻运动。即使DNN成功地再现了人类视觉的某些特质,更详细的调查也可以揭示人类与网络之间以及同一网络的不同实例之间的不一致性。从不同初始化训练的PredNets中旋转蛇错觉的不一致性表明,预测编码并不能可靠地导致类似人类的错觉运动。

英文摘要:

Why do we perceive illusory motion in some static images? Several accounts have been proposed based on eye movements, response latencies to different image elements, or interactions between image patterns and motion energy detectors. Recently, PredNet, a recurrent deep neural network (DNN) based on predictive coding principles, was reported to reproduce the "Rotating Snakes" illusion, suggesting a role for predictive coding in illusory motion. We replicate this finding and then use a series of "in silico psychophysics" experiments to examine whether PredNet behaves consistently with human observers for simplified variants of the illusory stimuli. We also measure response latencies to individual elements of the Rotating Snakes pattern by probing internal units in the network. A pretrained PredNet model predicted illusory motion for all subcomponents of the Rotating Snakes stimulus, consistent with human observers. However, we found no simple response delays in internal units, as found in physiological data. The PredNet model's detection of motion in gradients was based on contrast, not luminance, as it is in human perception. Finally, we tested the robustness of the illusion on 10 identical PredNets trained on the same video data; we found a large variation in the ability of the network to reproduce the illusion and predict motion for simplified variants of the illusion. Also, unlike human observers, none of the networks predicted illusory motion for greyscale variants of the pattern. Even when a DNN successfully reproduces some idiosyncrasy of human vision, a more detailed investigation can reveal inconsistencies between humans and the network and between different instances of the same network. The inconsistency of the Rotating Snakes illusion in PredNets trained from different initializations suggests that predictive coding does not reliably lead to human-like illusory motion.

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。

↑