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

Related Concept Videos

Labeling Emotion

Labeling Emotion

Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...

You might also read

Related Articles

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

Sort by

Same author

PDGrad: Guiding Diffusion Model for Reference-Based Blind Face Restoration with Pivot Direction Gradient Guidance.

Sensors (Basel, Switzerland)·2024

Same author

ETFT: Equiangular Tight Frame Transformer for Imbalanced Semantic Segmentation.

Sensors (Basel, Switzerland)·2024

Same author

ABDGAN: Arbitrary Time Blur Decomposition Using Critic-Guided TripleGAN.

Sensors (Basel, Switzerland)·2024

Same author

GammaGAN: Gamma-Scaled Class Embeddings for Conditional Video Generation.

Sensors (Basel, Switzerland)·2023

Same author

Image Recommendation System Based on Environmental and Human Face Information.

Sensors (Basel, Switzerland)·2023

Same author

Efficient Multi-Scale Stereo-Matching Network Using Adaptive Cost Volume Filtering.

Sensors (Basel, Switzerland)·2022

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 27, 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

Semantic Segmentation Using Pixel-Wise Adaptive Label Smoothing via Self-Knowledge Distillation for Limited Labeling

Sangyong Park¹, Jaeseon Kim¹, Yong Seok Heo^1,2

¹Department of Electrical and Computer Engineering, Ajou University, Suwon 16449, Korea.

Sensors (Basel, Switzerland)

|April 12, 2022

Summary

This summary is machine-generated.

This study introduces pixel-wise adaptive label smoothing (PALS), a new method to train deep convolutional neural networks for semantic segmentation with limited data. PALS improves accuracy by utilizing internal image statistics and self-knowledge distillation, overcoming overfitting challenges.

Keywords:

limited training data regularization self-knowledge distillation semantic segmentation

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Sep 27, 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

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Deep convolutional neural networks (DCNNs) demand extensive labeled data for high performance, which is costly for semantic segmentation due to pixel-level annotation requirements.
Training DCNNs with limited data often leads to overfitting and reduced accuracy, a significant challenge in practical semantic segmentation tasks.

Purpose of the Study:

To propose a novel regularization method, pixel-wise adaptive label smoothing (PALS), to enable stable training of semantic segmentation networks with limited datasets.
To leverage internal image statistics and self-knowledge distillation to mitigate accuracy degradation caused by data scarcity.

Main Methods:

PALS generates pixel-wise aggregated probability distributions using a similarity matrix that captures pixel affinities.
The method incorporates one-hot encoded ground-truth labels with aggregated distributions to create final soft labels.
Effectiveness was validated on the Cityscapes and Pascal VOC2012 datasets using varying percentages (10-100%) of training data.

Main Results:

PALS demonstrated improved accuracy in semantic segmentation tasks with limited training data compared to standard cross-entropy loss methods.
On the Cityscapes test set, PALS achieved notable mIoU improvements across all tested data subsets (10%, 30%, 50%, 100%).
Quantitative and qualitative comparisons confirmed the superior performance of PALS over existing methods.

Conclusions:

Pixel-wise adaptive label smoothing (PALS) is an effective regularization technique for training semantic segmentation DCNNs with limited data.
The proposed method successfully addresses the overfitting problem and enhances network accuracy by utilizing pixel-level image information.
PALS offers a practical solution for scenarios where acquiring large annotated datasets for semantic segmentation is infeasible.