FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios

2026-05-23

AI Summary

This work addresses the challenges of data scarcity and the absence of a unified benchmark in real-world food defect detection by introducing FDD-48, a fine-grained annotated dataset encompassing 13 food categories and 48 defect types. To tackle these limitations, the authors propose FDDet, a semi-supervised detection framework that incorporates a novel BBoxMixUp region-mixing augmentation strategy and a consistency-guided pseudo-label calibration (CGPC) mechanism. These innovations effectively mitigate feature confusion under limited training samples and reduce the impact of noisy pseudo-labels. Experimental results demonstrate that FDDet significantly outperforms state-of-the-art detectors on the FDD-48 benchmark, confirming its efficacy and robustness in data-constrained scenarios.

Abstract

Food defect detection is critical for automated quality control, yet existing studies lack unified benchmarks and suffer from data scarcity. We introduce FDD-48, a comprehensive dataset with fine-grained annotations across 13 food types and 48 defect categories under diverse real-world conditions. To improve detection with limited labeled data, we propose FDDet, a semi-supervised framework featuring two key components: (1) BBoxMixUp, a data augmentation technique that mixes same-category defect regions to reduce spurious feature associations, and (2) CGPC (Consistency-Guided Pseudo-Label Calibration), which filters pseudo-labels based on intra-sample consistency. Experiments show FDDet significantly outperforms mainstream detectors on FDD-48, demonstrating its effectiveness for food defect detection under data-limited scenarios.

Problem

• food defect detection
• data scarcity
• real-world scenarios
• unified benchmarks

Innovation

• FDDet
• BBoxMixUp
• CGPC
• semi-supervised learning
• food defect detection