Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ohamouddou, Mohamed, Ohamouddou, Said, Afia, Abdellatif El, Lasri, Rafik
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.20232
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914010643824640
author Ohamouddou, Mohamed
Ohamouddou, Said
Afia, Abdellatif El
Lasri, Rafik
author_facet Ohamouddou, Mohamed
Ohamouddou, Said
Afia, Abdellatif El
Lasri, Rafik
contents This study proposes ATMS-KD (Adaptive Temperature and Mixed-Sample Knowledge Distillation), a novel framework for developing lightweight CNN models suitable for resource-constrained agricultural environments. The framework combines adaptive temperature scheduling with mixed-sample augmentation to transfer knowledge from a MobileNetV3 Large teacher model (5.7\,M parameters) to lightweight residual CNN students. Three student configurations were evaluated: Compact (1.3\,M parameters), Standard (2.4\,M parameters), and Enhanced (3.8\,M parameters). The dataset used in this study consists of images of \textit{Rosa damascena} (Damask rose) collected from agricultural fields in the Dades Oasis, southeastern Morocco, providing a realistic benchmark for agricultural computer vision applications under diverse environmental conditions. Experimental evaluation on the Damascena rose maturity classification dataset demonstrated significant improvements over direct training methods. All student models achieved validation accuracies exceeding 96.7\% with ATMS-KD compared to 95--96\% with direct training. The framework outperformed eleven established knowledge distillation methods, achieving 97.11\% accuracy with the compact model -- a 1.60 percentage point improvement over the second-best approach while maintaining the lowest inference latency of 72.19\,ms. Knowledge retention rates exceeded 99\% for all configurations, demonstrating effective knowledge transfer regardless of student model capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20232
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems
Ohamouddou, Mohamed
Ohamouddou, Said
Afia, Abdellatif El
Lasri, Rafik
Computer Vision and Pattern Recognition
This study proposes ATMS-KD (Adaptive Temperature and Mixed-Sample Knowledge Distillation), a novel framework for developing lightweight CNN models suitable for resource-constrained agricultural environments. The framework combines adaptive temperature scheduling with mixed-sample augmentation to transfer knowledge from a MobileNetV3 Large teacher model (5.7\,M parameters) to lightweight residual CNN students. Three student configurations were evaluated: Compact (1.3\,M parameters), Standard (2.4\,M parameters), and Enhanced (3.8\,M parameters). The dataset used in this study consists of images of \textit{Rosa damascena} (Damask rose) collected from agricultural fields in the Dades Oasis, southeastern Morocco, providing a realistic benchmark for agricultural computer vision applications under diverse environmental conditions. Experimental evaluation on the Damascena rose maturity classification dataset demonstrated significant improvements over direct training methods. All student models achieved validation accuracies exceeding 96.7\% with ATMS-KD compared to 95--96\% with direct training. The framework outperformed eleven established knowledge distillation methods, achieving 97.11\% accuracy with the compact model -- a 1.60 percentage point improvement over the second-best approach while maintaining the lowest inference latency of 72.19\,ms. Knowledge retention rates exceeded 99\% for all configurations, demonstrating effective knowledge transfer regardless of student model capacity.
title ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.20232