Distilling Knowledge to Efficient Transformer for Semi-Supervised Citrus Maturity Detection using Consumer UAVs
Ahmad, Jamil Khan, Mustaqeem Gueaieb, Wail Saddik, Abdulmotaleb El De Masi, Giulia Karray, Fakhri
Ahmad, Jamil
Khan, Mustaqeem
Gueaieb, Wail
Saddik, Abdulmotaleb El
De Masi, Giulia
Karray, Fakhri
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Accurate detection of citrus fruit maturity is critical for optimizing harvest schedules and maximizing yield. Consumer-grade unmanned aerial vehicles (UAVs) have emerged as cost-effective alternatives to traditional methods for detecting maturity, which rely on labor-intensive manual inspections. This paper presents a two-step, semi-supervised approach leveraging knowledge distillation (KD) and transfer learning for citrus maturity detection in UAV images. Specifically, we combine teacher-filtered pseudo-labels with a consistency-guided feature distillation signal to exploit abundant unlabeled UAV frames while using only a small labeled seed set. Firstly, a consistency-guided KD transfers knowledge from a pretrained detection transformer with collaborative hybrid assignment training (Co-DETR) to a lightweight student network by exploiting a small labeled and a large unlabeled dataset. The student network (Cit-DETR) is based on the highly efficient detection transformer (RT-DETR) having a ResNet18 backbone with selective kernel blocks and the hybrid encoder module. Step 2 uses a small labeled augmented dataset with maturity labels to fine-tune the Cit-DETR model for maturity detection. Experimental results on a custom UAV-captured citrus dataset demonstrate the effectiveness of our method, achieving 86.2% average precision in citrus detection and 91.0% mean average precision in ripeness detection. The model has been further optimized for real-time inference on edge devices or UAVs, enabling precision agriculture applications.
Citation
J. Ahmad, M. Khan, W. Gueaieb, A.E. Saddik, G. De Masi, F. Karray, "Distilling Knowledge to Efficient Transformer for Semi-Supervised Citrus Maturity Detection using Consumer UAVs," IEEE Transactions on Consumer Electronics, vol. PP, no. 99, pp. 1-1, 2026, https://doi.org/10.1109/tce.2026.3659120.
Source
IEEE Transactions on Consumer Electronics
Conference
Keywords
40 Engineering, 4008 Electrical Engineering, 4009 Electronics, Sensors and Digital Hardware
Subjects
Source
Publisher
IEEE