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 Experiment Video

Updated: Mar 19, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

853

SCADA: Sparse cross attention for domain adaptive semantic segmentation.

Qizhe Fan1, Xiaoqin Shen1, Yuanbo Chen2

  • 1School of Mathematics, Xi'an University of Technology, Xi'an, 710054, China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 18, 2026
PubMed
Summary

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

Molecular cloning and heterologous expression of an acid-stable endoxylanase gene from Penicillium oxalicum in Trichoderma reesei.

Journal of microbiology and biotechnology·2013
Same author

Increasing gastric juice pH level prior to anti-Helicobacter pylori therapy may be beneficial to the healing of duodenal ulcers.

Experimental and therapeutic medicine·2013
Same author

Inhibitory effect of glutathione on oxidative liver injury induced by dengue virus serotype 2 infections in mice.

PloS one·2013
Same author

Efficacy of tribendimidine against Angiostrongylus cantonensis infection in the mice.

Parasitology research·2013
Same author

Double-bundle anatomical versus single-bundle isometric medial patellofemoral ligament reconstruction for patellar dislocation.

International orthopaedics·2013
Same author

Fatty acid binding proteins FABP9 and FABP10 participate in antibacterial responses in Chinese mitten crab, Eriocheir sinensis.

PloS one·2013
Same journal

Observer-based ADP for secure resource allocation in high-order nonlinear multi-agent systems under FDI attacks.

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

Concept mask-aware pruning and augmentation for few sample model compression.

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

Hindsight-based state space exploration via counterfactual intrinsic reward assignment.

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

Integrating visual and language cues via state space models for medical image segmentation.

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

DNA: Improving text-based person search through distillation learning, negated relation-aware learning, and augmented representation learning.

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

MCFusion-DDI: Multimodal cross-attention fusion of local-global features and latent drug associations for explainable DDI prediction.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles
This summary is machine-generated.

This study introduces a sparse cross attention (SCA) block for unsupervised domain adaptive semantic segmentation, reducing computational costs. It also enhances pixel discrimination through contrastive learning, improving model performance on real-world images.

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Unsupervised domain adaptive (UDA) semantic segmentation aims to predict semantic labels for unannotated target images using models trained on annotated source data.
  • Existing attention mechanisms in UDA often overlook large-region semantic categories, leading to inefficient computations and wasted resources.
  • Current UDA methods frequently neglect the inherent connections within training data, hindering effective pixel discrimination.

Purpose of the Study:

  • To propose an efficient sparse cross attention (SCA) block to reduce computational redundancy in UDA semantic segmentation.
  • To enhance pixel discrimination by incorporating pixel-wise contrastive learning within the UDA framework.
  • To improve the overall performance and efficiency of UDA semantic segmentation models.
Keywords:
Attention mechanismContrastive learningDomain adaptationSemantic segmentation

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

1.2K

Related Experiment Videos

Last Updated: Mar 19, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

853
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

1.2K

Main Methods:

  • Developed a sparse cross attention (SCA) block that aggregates contextual information horizontally and vertically to create sparse attention maps.
  • Implemented pixel-wise contrastive learning in the latent space of extracted features to promote intra-class compactness and inter-class separability.
  • Evaluated the proposed SCA block and contrastive learning strategy on GTA → Cityscapes, Synthia → Cityscapes, and Cityscapes → Dark Zurich benchmarks.

Main Results:

  • The SCA block significantly reduces computational resources, leading to lower time and space complexity.
  • The proposed method demonstrates substantial performance improvements on three widely-used UDA benchmarks.
  • Integrating SCA with existing UDA methods further enhances their performance, showing broad applicability.

Conclusions:

  • The proposed SCA block offers an efficient solution for UDA semantic segmentation by addressing computational inefficiencies.
  • Pixel-wise contrastive learning effectively improves pixel representation discrimination across domains.
  • The SCA block is a versatile component that can be integrated into various UDA frameworks to boost performance.