Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Ruihao, Liu, Yong, Tang, Yansong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.24508
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911713202274304
author Xu, Ruihao
Liu, Yong
Tang, Yansong
author_facet Xu, Ruihao
Liu, Yong
Tang, Yansong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24508
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios
Xu, Ruihao
Liu, Yong
Tang, Yansong
Computer Vision and Pattern Recognition
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.
title FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.24508