ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing

2026-07-06

AI Summary

This work addresses the limited generalization of industrial defect detection in unseen scenarios and the absence of fine-grained assessment of defect severity. To this end, it introduces the first large-scale industrial dataset featuring both pixel-level annotations and severity labels aligned with industry standards, established through a novel dual-track benchmark that jointly tackles cross-scenario defect detection and four-level severity grading. Leveraging high-resolution microscopic images and multi-scenario data, deep learning methods are employed to achieve integrated defect detection, localization, classification, and severity assessment. The associated challenge attracted 86 participating teams, with 21 submitting results and 12 releasing their models and technical reports, thereby establishing a new benchmark for industrial defect analysis.

Abstract

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. To address these limitations, we design two complementary tracks: Track 1 (Cross-Scenario Defect Detection) targets accurate defect detection, localization, and classification across diverse unseen production environments; Track 2 (Fine-Grained Severity Grading) requires assigning each detected defect an industry-standard severity level, including Acceptable, Marginal NG, NG, and Gross NG. We construct a large-scale industrial dataset of high-resolution microscopic images spanning seven representative defect categories, comprising over 3,800 images with pixel-level instance annotations for Track 1 and over 2,600 images with severity-grade labels for Track 2. The challenge attracted 86 registered participants with 130 submissions; during the final testing phase, 21 teams submitted results and 12 teams provided models with technical reports. The resulting benchmark, together with the diverse and effective solutions contributed by participating teams, sets a new standard for industrial defect analysis research.

Problem

• Cross-Scenario Defect Detection
• Fine-Grained Severity Grading
• Industrial Defect Inspection
• Unseen Production Scenarios
• Severity-Aware Assessment

Innovation

• Cross-Scenario Defect Detection
• Fine-Grained Severity Grading
• Industrial Defect Inspection
• High-Precision Manufacturing
• Pixel-Level Annotation