arXiv subjects

Eiji Watanabe

Publications and source records attributed to Eiji Watanabe.

5 recordsLinked to original sources

arXiv2026

Motion Illusions Generated Using Predictive Neural Networks Also Fool Humans

Why do we sometimes perceive static images as if they were moving? Visual motion illusions enjoy a sustained popularity, yet there is no definitive answer to the question of why they work. Here we present evidence in favor of the hypothesis that illusory motion is a side effect of the predictive abilities of the brain. We present a generative model, the Evolutionary Illusion GENerator (EIGen), that creates new visual motion illusions based on a video predictive neural network. We confirm that the constructed illusions are effective on human participants through a psychometric survey. Our results support the hypothesis that illusory motion might be the consequence of perceiving the brain's own predictions rather than perceiving raw visual input from the eyes. The philosophical motivation of this paper is to call attention to the untapped potential of "motivated failures", ways for artificial systems to fail as biological systems fail, as a worthy outlet for Artificial Intelligence and Artificial Life research.

cs.NE↗

arXiv2024

Using SlowFast Networks for Near-Miss Incident Analysis in Dashcam Videos

This paper classifies near-miss traffic videos using the SlowFast deep neural network that mimics the characteristics of the slow and fast visual information processed by two different streams from the M (Magnocellular) and P (Parvocellular) cells of the human brain. The approach significantly improves the accuracy of the traffic near-miss video analysis and presents insights into human visual perception in traffic scenarios. Moreover, it contributes to traffic safety enhancements and provides novel perspectives on the potential cognitive errors in traffic accidents.

cs.AI↗

arXiv2022

Artificial Perception Meets Psychophysics, Revealing a Fundamental Law of Illusory Motion

Rotating Snakes is a visual illusion in which a stationary design is perceived to move dramatically. In the current study, the mechanism that generates perception of motion was analyzed using a combination of psychophysics experiments and deep neural network models that mimic human vision. We prepared three- and four-color illusion-like designs with a wide range of luminance and measured their strength of induced rotational motion. As a result, we discovered the fundamental law that the effect of the four-color snake rotation illusion was successfully enhanced by the combination of two perceptual motion vectors produced by the two three-color designs. In years to come, deep neural network technology will be one of the most effective tools not only for engineering applications but also for human perception research.

q-bio.NC↗

arXiv2022

Motion Illusion-like Patterns Extracted from Photo and Art Images Using Predictive Deep Neural Networks

In our previous study, we successfully reproduced the illusory motion of the rotating snakes illusion using deep neural networks incorporating predictive coding theory. In the present study, we further examined the properties of the networks using a set of 1500 images, including ordinary static images of paintings and photographs and images of various types of motion illusions. Results showed that the networks clearly classified illusory images and others and reproduced illusory motions against various types of illusions similar to human perception. Notably, the networks occasionally detected anomalous motion vectors, even in ordinally static images where humans were unable to perceive any illusory motion. Additionally, illusion-like designs with repeating patterns were generated using areas where anomalous vectors were detected, and psychophysical experiments were conducted, in which illusory motion perception in the generated designs was detected. The observed inaccuracy of the networks will provide useful information for further understanding information processing associated with human vision.

q-bio.NC↗

arXiv2021

Impact of GPU uncertainty on the training of predictive deep neural networks

[retracted] We found out that the difference was dependent on the Chainer library, and does not replicate with another library (pytorch) which indicates that the results are probably due to a bug in Chainer, rather than being hardware-dependent. -- old abstract Deep neural networks often present uncertainties such as hardware- and software-derived noise and randomness. We studied the effects of such uncertainty on learning outcomes, with a particular focus on the function of graphics processing units (GPUs), and found that GPU-induced uncertainty increased learning accuracy of a certain deep neural network. When training a predictive deep neural network using only the CPU without the GPU, the learning error is higher than when training the same number of epochs using the GPU, suggesting that the GPU plays a different role in the learning process than just increasing the computational speed. Because this effect cannot be observed in learning by a simple autoencoder, it could be a phenomenon specific to certain types of neural networks. GPU-specific computational processing is more indeterminate than that by CPUs, and hardware-derived uncertainties, which are often considered obstacles that need to be eliminated, might, in some cases, be successfully incorporated into the training of deep neural networks. Moreover, such uncertainties might be interesting phenomena to consider in brain-related computational processing, which comprises a large mass of uncertain signals.

cs.LG↗