Search research articles

Related Concept Videos

Perceptual Constancy

Perceptual Constancy

Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...

You might also read

Related Articles

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

Sort by

Same author

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data.

Sensors (Basel, Switzerland)·2024

See all related 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: Aug 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Revisiting Consistency for Semi-Supervised Semantic Segmentation.

Ivan Grubišić¹, Marin Oršić², Siniša Šegvić¹

¹Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia.

Sensors (Basel, Switzerland)

|January 21, 2023

Summary

This summary is machine-generated.

Semi-supervised learning for dense prediction models significantly reduces the need for labeled data. This study demonstrates that one-way consistency with strong photometric and geometric perturbations yields superior results, even outperforming coarse supervised training.

Keywords:

deep learning dense prediction one-way consistency scene understanding semantic segmentation semi-supervised learning

More Related Videos

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Aug 13, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Deep learning models, particularly for dense prediction tasks like semantic segmentation, heavily rely on large amounts of pixel-level annotated data, which is costly and time-consuming to acquire.
Semi-supervised learning offers a promising approach to mitigate this data dependency by leveraging unlabeled data.

Purpose of the Study:

To investigate and optimize semi-supervised learning strategies for efficient deep models in dense prediction tasks.
To evaluate the impact of different perturbation techniques and consistency enforcement methods on model performance.

Main Methods:

The study explores semi-supervised algorithms enforcing prediction consistency over perturbed unlabeled inputs.
A novel competitive perturbation model combining geometric warp and photometric jittering is proposed.
Experiments focus on efficient model architectures suitable for real-time applications.

Main Results:

One-way consistency, where only one model instance is perturbed and its gradient is backpropagated, shows clear advantages.
Perturbing only the 'student' branch within the model architecture further enhances performance.
The proposed perturbation model, particularly its photometric component, significantly outperforms recent methods.

Conclusions:

Semi-supervised learning with optimized perturbation strategies is highly effective for dense prediction, reducing reliance on extensive labeled data.
The proposed approach, especially when applied to efficient models, demonstrates potential to surpass traditional supervised methods using coarse annotations, as evidenced by Cityscapes dataset experiments.