Generative Inference Demo

This demo showcases how neural networks can perceive visual illusions and develop Gestalt principles of perceptual organization through generative inference.

📄 Paper: Generative Inference unifies feedback processing for learning and perception in natural and artificial vision

How to use this demo:

• Load pre-configured examples: Click on any visual illusion below and hit "Load Parameters" to automatically set up the optimal parameters for that illusion
• Run the inference: After loading parameters or setting your own, hit "Run Inference" to start the generative inference process
• You can also upload your own images and experiment with different parameters to see how they affect the generative inference process

Visual Illusion Examples

Select an illusion to load its parameters and see how generative inference reveals perceptual effects

About Generative Inference

Generative inference is a technique that reveals how neural networks perceive visual stimuli. This demo primarily uses the Prior-Guided Drift Diffusion method.

Prior-Guided Drift Diffusion

Moving away from a noisy representation of the input images

IncreaseConfidence

Moving away from the least likely class identified at iteration 0 (fast perception)

Parameters:

• Drift Noise: Controls the amount of noise added to the image at the beginning
• Diffusion Noise: Controls the amount of noise added at each optimization step
• Update Rate: Learning rate for the optimization process
• Number of Iterations: How many optimization steps to perform
• Model Layer: Select a specific layer of the ResNet50 model to extract features from
• Epsilon (Stimulus Fidelity): Controls the size of perturbation during optimization

Generative Inference was developed by Tahereh Toosi.