Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Vision as Bayesian inference: analysis by synthesis?

Alan Yuille¹, Daniel Kersten

¹Department of Statistics, UCLA, San Francisco, CA 94115, USA. yuille@stat.ucla.edu

Trends in Cognitive Sciences

|June 21, 2006

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Scaling 3D Compositional Models for Robust Classification and Pose Estimation.

Proceedings. IEEE International Conference on Computer Vision·2026

Same author

A comprehensive survey of AI agents in healthcare.

Journal of biomedical informatics·2026

Same author

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More.

Proceedings of machine learning research·2026

Same author

Hyperplasia Functions as a Link between Obesity and Cancer.

Cancer research·2026

Same author

Mamba-Reg: Vision Mamba Also Needs Registers.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2025

Same author

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2025

Same journal

Multi-brain neurofeedback: what are we training for?

Trends in cognitive sciences·2026

Same journal

The developing vocal self.

Trends in cognitive sciences·2026

Same journal

Searching beyond decrements: Attentional guidance across the adult lifespan.

Trends in cognitive sciences·2026

Same journal

Looking into working memory through micro eye movements.

Trends in cognitive sciences·2026

Same journal

Timescapes of non-human experience.

Trends in cognitive sciences·2026

Same journal

Building word meanings from memories and predictions.

Trends in cognitive sciences·2026

See all related articles

Studying human vision requires natural images, not artificial ones, to avoid errors. Bayesian inference and "analysis by synthesis" offer a complex yet effective approach to understanding visual systems.

Area of Science:

Cognitive Science
Computer Vision
Neuroscience

Background:

Understanding human vision is complex due to the intricate nature of natural images.
Artificial stimuli may lead to inaccurate generalizations about visual perception.
Traditional approaches may not fully capture the complexities of real-world visual tasks.

Purpose of the Study:

To advocate for studying human vision using natural images and tasks.
To propose Bayesian inference as a framework for developing theories of vision.
To explore 'analysis by synthesis' strategies and their relevance to the brain.

Main Methods:

Utilizing Bayesian inference on structured probability distributions.
Applying 'analysis by synthesis' principles.

Related Experiment Videos

Examining recent computer vision examples.

Main Results:

Bayesian inference provides a method to handle the complexity of natural images in vision theories.
'Analysis by synthesis' strategies show parallels with brain mechanisms.
The proposed framework offers a more robust approach to understanding visual systems.

Conclusions:

Research on human vision should prioritize naturalistic stimuli and tasks.
Bayesian inference and 'analysis by synthesis' are promising theoretical tools for vision science.
These approaches have significant implications for cognitive science and understanding the brain.