Safety
Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection
arXiv:2512.06171v2 Announce Type: replace Abstract: Shearography is an interferometric technique sensitive to surface displacement gradients, providing high sensitivity for detecting subsurface defect
arXiv:2512.06171v2 Announce Type: replace Abstract: Shearography is an interferometric technique sensitive to surface displacement gradients, providing high sensitivity for detecting subsurface defects in safety-critical components. A key limitation to industrial adoption is the lack of high-quality annotated datasets, since manual labeling remains labor-intensive, subjective, and difficult to standardize. We present an automated labeling pipeline that generates candidate defect bounding boxes with Grounded DINO, refines them using SAM masks, and exports YOLO-format labels for downstream detector training. Quantitative evaluation shows the generated boxes are suitable for weakly supervised learning, while high-resolution masks provide qualitative visualization. This approach reduces manual effort and supports scalable dataset creation for robust industrial defect detection.
Related
- Weakly supervised framework for wildlife detection and counting in challenging Arctic environments: a case study on caribou (Rangifer tarandus)
- OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection
- Contour Refinement using Discrete Diffusion in Low Data Regime
- CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
- Weakly-Supervised Referring Video Object Segmentation through Text Supervision
Source: arXiv cs.CV | 2026-04-24