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 Video

Updated: Jun 24, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Ecological Vision Hypothesis: Training Deep Neural Networks for Robustness and Human Alignment.

Frank Tong^1,2, Hojin Jang³

¹1Department of Psychology, Vanderbilt University, Nashville, Tennessee, USA;

Annual Review of Vision Science

|June 22, 2026

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

Exposure to naturalistic occlusion promotes generalized, human-like robustness in deep neural networks.

bioRxiv : the preprint server for biology·2026

Same author

Clinical Efficacy and Tolerability of Sorafenib in Dogs With Advanced Carcinomas.

Veterinary and comparative oncology·2026

Same author

Emergence of form-independent direction selectivity in human V3A and MT.

Journal of vision·2025

Same author

Advancing Medical Image Perception and Quality Assessment Through Technology and Human Factors Research.

Journal of medical imaging (Bellingham, Wash.)·2025

Same author

A reevaluation of the visual phantom illusion and its impact on the motion aftereffect.

Scientific reports·2025

Same author

Category-specific perceptual learning of robust object recognition modelled using deep neural networks.

PLoS computational biology·2025

Same journal

The Legacy of Perley G. Nutting Jr.: The Past and the Present of Chromatic Discrimination.

Annual review of vision science·2026

Same journal

Approaching Visual Perception with Spatiotemporally Patterned Optogenetic Stimulation.

Annual review of vision science·2026

Same journal

Subcortical Foundations of Binocular Vision: Circuits and Computation from Retina to Cortex and Back.

Annual review of vision science·2026

Same journal

Visual Perception of 3D Shape: From Local 2D Image Measurements to 3D Surface Properties.

Annual review of vision science·2026

Same journal

Reexamining the Relationship Between Stereopsis and Motion Parallax.

Annual review of vision science·2026

Same journal

Aphantasia and the Mechanisms of Visual Mental Imagery.

Annual review of vision science·2026

See all related articles

Deep neural networks (DNNs) show promise but lack human vision robustness. Training DNNs with ecologically relevant challenges, like blur, could improve their flexibility and alignment with human visual perception.

Area of Science:

Neuroscience
Computer Vision
Cognitive Science

Background:

Deep neural networks (DNNs) are advanced neurocomputational models of the visual system.
While DNNs excel at predicting neural responses to clear images, they exhibit brittleness under ambiguous viewing conditions.
Human vision demonstrates remarkable robustness to challenges like noise, blur, and occlusion, unlike typical DNNs.

Purpose of the Study:

To investigate the ecological vision hypothesis for improving DNN robustness.
To explore how training DNNs with ecologically relevant visual challenges enhances human-like visual processing.
To understand the role of blur in visual perception and its implications for DNN development.

Main Methods:

Discussing the ecological vision hypothesis.

Related Experiment Videos

Last Updated: Jun 24, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Analyzing the limitations of current DNNs in handling visual ambiguities.

Proposing training strategies for DNNs based on human visual experience.

Main Results:

DNNs trained on standard datasets lack the robustness of human vision.
Challenging viewing conditions, prevalent in natural environments, are key to acquiring robust vision.
Blur may shift visual processing from local texture to global shape sensitivity.

Conclusions:

The ecological vision hypothesis suggests training DNNs with naturalistic challenges can improve robustness.
DNNs trained with ecologically relevant data, particularly 3D scene and shape information, are expected to align better with human vision.
Addressing DNN brittleness requires incorporating the complexities of real-world visual input.