Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
April 19, 2026Journal of King Saud University - Computer and Information SciencesOpen Access

ASCR-DETR: Enhanced industrial fabric defect detection with Adaptive Spatial Geometry Convolution and Context-Guided Spatial Reconstruction

View Full Paper
Ask AI
Bookmark
Share

Authors

JLJiajun LiuQFQiang FuJLJing Li

Discussion

Loading...

Member takes

Overview

Demonstrates improved fabric defect detection in industrial settings, suggesting enhancements to textile quality assurance.

Key Points

  • The aim is to improve fabric defect detection accuracy in complex industrial environments by developing the ASCR-DETR system.
  • Proposed Adaptive Spatial Geometric Convolution module for dynamic defect geometry modeling.
  • Developed Context-Guided Spatial Reconstruction Feature Pyramid Fusion Network for multi-resolution information aggregation.
  • Implemented Coordinate Attention mechanisms for enhanced contextual representation.
  • Introduced Dynamic Range Histogram Self-Attention for effective intra-scale feature interaction.
  • Achieved 85.3% mean Average Precision at 50% Intersection over Union, an increase of 7.1%.
  • Reached 45.9% mean Average Precision across the range of 50:95%, up by 4.9%.
  • Outperformed both CNN-based and Transformer-based defect detection methods.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69e472a8010ef96374d8e9cbhttps://doi.org/10.1007/s44443-026-00642-5
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1FAC-DETR: a lightweight fabric defect detection model integrating Fourier convolution and multiscale linear attention2026
  2. 2REDef-DETR: real-time and efficient DETR for industrial surface defect detection2024 · 32 citations
  3. 3FDDNet: Fabric defect detection with spatial depth-transforming convolution and multiscale dilated self-attention fusion module2025
  4. 4Texture-aware and defect-guided swin transformer for multi-scale textile defect segmentation2026
  5. 5EAS-DETR: An Enhanced Real-Time Transformer with Sparse Attention and Global Context for PCB Defect Inspection2026