Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Survival Tree01:19

Survival Tree

191
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
191
Associative Learning01:27

Associative Learning

752
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
752

You might also read

Related Articles

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

Sort by
Same author

Development of sustainable gel systems with thermo-sensitive properties by enzymatic modification of upcycled rice cake flour.

Food chemistry: X·2026
Same author

Detection of lumpy skin disease virus belonging to cluster 2.5 in flies collected during the outbreak in the Republic of Korea.

Acta tropica·2026
Same author

Interventional treatments for sacroiliac joint pain: a systematic review and network meta-analysis.

Regional anesthesia and pain medicine·2026
Same author

Leveraging contextual confidence for smarter retrieval in large language models.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Text Mining of CVD Synthesis Recipes for 2D Materials.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Repetition-rate-tunable femtosecond mode-locked Yb:GYSO laser in the sub-GHz regime.

Optics express·2025

Related Experiment Video

Updated: Oct 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

587

SAR ATR for Limited Training Data Using DS-AE Network.

Ji-Hoon Park1, Seung-Mo Seo1, Ji-Hee Yoo1

  • 1Agency for Defense Development, Daejeon 34186, Korea.

Sensors (Basel, Switzerland)
|July 20, 2021
PubMed
Summary

This study introduces a novel Double Squeeze-Adaptive Excitation (DS-AE) network to improve automatic target recognition (ATR) in synthetic aperture radar (SAR) images. The DS-AE network enhances classifier performance, especially with limited training data.

Keywords:
automatic target recognition (ATR)channel attentionconvolutional neural network (CNN)deep learningdouble-squeeze-adaptive-excitation networklimited labeled datasynthetic aperture radar (SAR)

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

725

Related Experiment Videos

Last Updated: Oct 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

587
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

725

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Signal Processing

Background:

  • Automatic target recognition (ATR) using synthetic aperture radar (SAR) images is crucial.
  • Limited labeled SAR target data significantly degrades classifier performance.

Purpose of the Study:

  • To propose a novel Double Squeeze-Adaptive Excitation (DS-AE) network to overcome performance degradation in SAR target recognition with limited training data.
  • To enhance channel attention mechanisms for improved feature extraction in SAR imagery.

Main Methods:

  • A modified ResNet18 architecture incorporating new channel attention modules (DS-AE network).
  • The DS-AE network utilizes additional fully connected layers for the squeeze operation to preserve channel information.
  • A novel parametric sigmoid activation function is employed for the excitation operation to adaptively emphasize useful channel information.

Main Results:

  • The DS-AE network demonstrated significantly improved SAR target recognition performance on small training datasets.
  • Performance comparisons were made against a standard convolutional neural network (CNN) and a CNN with conventional SE channel attention modules.
  • The DS-AE network outperformed both baseline models when the number of training images was reduced.

Conclusions:

  • The proposed DS-AE network effectively addresses the challenge of limited training data in SAR target recognition.
  • The novel channel attention mechanism enhances the robustness and accuracy of ATR systems for SAR images.
  • DS-AE offers a promising solution for improving the practical application of SAR-based ATR systems.