Vis-Lens generates preferred visual representations in neural networks and human brain using fMRI
Original title: Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks
Vis-Lens integrates a variational autoencoder and diffusion model to generate realistic preferred images by modifying activation-regularized latent codes.
We propose a structured visual representations landscape with an activation-based prior to regularize the landscape using activations from brain regions or neural network units. Our model Vis-Lens integrates a variational autoencoder and a diffusion model into an image generation framework. It enables generation of natural, realistic preferred images by directly modifying activation-regularized latent codes without per-image iterative optimization. We demonstrate effectiveness on artificial neural networks and human visual cortex using fMRI data, improving activation modulation and image realism over state-of-the-art.
- Improves activation modulation and image realism compared to state-of-the-art.
- Demonstrated on artificial neural networks and human visual cortex.
- Uses fMRI data for brain regions activations.
From the original article
1 min read at arxiv.orgUnderstanding how neurons respond to visual stimulus is an important question in both deep learning and neuroscience. It has significant implications for enhancing the interpretability of black-box artificial neural networks and for understanding the visual representation in the human brain.
By Yusong Zhao · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.