Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 15, 2025Journal of Computational Design and EngineeringOpen Access

VPGFNet: Cross-Domain Few-Shot Visual Prompt Graph Fusion Network for Industrial Defect Segmentation

View Full Paper
Ask AI
Bookmark
Share

Authors

ZYZhao YangQCQi ChenYDYi Du

Discussion

Loading...

Member takes

Overview

Proposed VPGFNet enhances defect segmentation in industrial settings, showing improved stability and adaptability.

Key Points

  • VPGFNet achieves a 4.8% improvement in 1-shot defect segmentation compared to existing methods.
  • The grid-based visual prompting module enhances local perception, aiding defect identification.
  • The method demonstrates superior adaptability in domain-shifted scenarios, overcoming challenges of limited data.
  • Experiments across three datasets highlight VPGFNet's effectiveness, outperforming state-of-the-art techniques.

Cite This Study

Yang et al. (2025) studied this question.

synapsesocial.com/papers/68f01110f081da0584b56996https://doi.org/10.1093/jcde/qwaf105
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. 1High-fidelity lensless imaging with single hologram based on physics-guided frequency-aware network2024 · 10 citations
  2. 2Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation2025 · 1 citations
  3. 3Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives2022 · 289 citations
  4. 4Multiscale Adaptive Prototype Transformer Network for Few-Shot Strip Steel Surface Defect Segmentation2025 · 9 citations
  5. 5Hierarchical Dense Correlation Distillation for Few-Shot Segmentation2023 · 166 citations