FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios
For practitioners in automated food quality control, this work provides a unified benchmark and a data-efficient detection method to address data scarcity in real-world scenarios.
The paper introduces FDD-48, a new dataset for food defect detection with 48 defect categories across 13 food types, and proposes FDDet, a semi-supervised framework with BBoxMixUp augmentation and CGPC pseudo-label calibration, achieving significant improvements over mainstream detectors under data-limited conditions.
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.