SePArate is a weakly supervised method for segmenting patterns from defects in semiconductor wafers. It uses only image‑level annotations and follows a three‑phase training process: encoder pretraining, knowledge transfer for spatial cues, and training on synthetic mixed‑defect data. Experiments show that SePArate outperforms baseline approaches in pixel‑level defect segmentation.
arXiv:2604. 26633v2 Announce Type: replace-cross Abstract: Industrial surface defect inspection suffers from a fundamental data bottleneck: defects are rare, annotations require expert knowledge, and collecting balanced training sets is slow and costly.
The paper introduces ISP-AD, the largest publicly available industrial anomaly detection dataset, featuring both synthetic and real defects from a factory floor. It focuses on challenging, small, weakly contrasted surface defects within highly variable structured patterns, addressing the bias of existing datasets toward ideal imaging conditions. Experiments demonstrate that even a small amount of weakly labeled real defects improves model generalization and that synthetic defects can serve as a useful cold‑start baseline for scalable training.
This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation when deployed in unseen production scenarios, and (2) most benchmarks neglect severity-aware assessment, which is critical for risk control and yield optimization.
The paper introduces an automated defect detection system for printed circuit board (PCB) pin insertion, combining U‑Net semantic segmentation with contour‑based feature extraction and logistic regression for board‑level pass/fail classification. Segmentation masks generate contour representations of individual pins, from which features such as average contour size are extracted to train the classifier. Evaluated on an industrial dataset and a public PCB pin‑inspection dataset, the method achieved ROC‑AUC scores of 0.990 and 1.000, outperforming PatchCore and instance‑segmentation baselines.
arXiv:2606. 08908v1 Announce Type: cross Abstract: Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination.
arXiv:2607. 12245v1 Announce Type: cross Abstract: Few-shot industrial defect detection remains difficult for standard supervised detectors, which achieve poor performance on boundary-dominated industrial defects.
arXiv:2608. 07770v1 Announce Type: new Abstract: Automated anomaly detection methods often report strong performance on curated academic benchmarks, but their behavior under real-world industrial conditions is less clear.
arXiv:2608. 13937v1 Announce Type: cross Abstract: Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production system but also aid in intelligent manufacturing management.
arXiv:2607. 21577v1 Announce Type: cross Abstract: Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection.
The paper introduces Contrastive Dual Gaussian Processes (CDGP), a weakly supervised approach for anomaly segmentation in industrial visual inspection. CDGP models normal and anomaly predictive distributions over dense tokens, using a posterior-dominance statistic that normalizes predictive-mean differences by joint uncertainty to provide spatial evidence and image-level confidence. The method achieves top performance on MVTec AD~2, KSDD2, and VisA datasets without requiring pixel-level annotations or test-time fitting.
PCB-MC is a new dataset for detecting missing components on printed circuit boards, featuring 197 distinct board types with footprint-level annotations derived from the RF100 dataset. The dataset includes multiple augmented samples per board type and introduces board type-aware cross‑validation splits to prevent layout leakage between training and test sets. Benchmark results show that supervised models suffer high false‑negative rates on unseen board designs, while unsupervised anomaly detection methods fail due to misalignment with board-specific references, highlighting the remaining challenges in missing component detection across diverse PCB layouts.
arXiv:2606. 00852v1 Announce Type: cross Abstract: Printed circuit board (PCB) defect detection is challenging because many defects are small and difficult to distinguish from complex background patterns.