Improving Lightweight Weed Detection via Knowledge Distillation

• URL: http://arxiv.org/abs/2507.12344v1
• Date: Wed, 16 Jul 2025 15:38:07 GMT
• Title: Improving Lightweight Weed Detection via Knowledge Distillation
• Authors: Ahmet Oğuz Saltık, Max Voigt, Sourav Modak, Mike Beckworth, Anthony Stein,
• Abstract summary: We investigate Channel-wise Knowledge Distillation (CWD) and Masked Generative Distillation (MGD) to enhance the performance of lightweight models for real-time smart spraying systems.<n>CWD and MGD effectively transfer knowledge from the teacher to the student model.<n>We validate real-time deployment feasibility by evaluating the student YOLO11n model on Jetson Orin Nano and Raspberry Pi 5 embedded devices.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weed detection is a critical component of precision agriculture, facilitating targeted herbicide application and reducing environmental impact. However, deploying accurate object detection models on resource-limited platforms remains challenging, particularly when differentiating visually similar weed species commonly encountered in plant phenotyping applications. In this work, we investigate Channel-wise Knowledge Distillation (CWD) and Masked Generative Distillation (MGD) to enhance the performance of lightweight models for real-time smart spraying systems. Utilizing YOLO11x as the teacher model and YOLO11n as both reference and student, both CWD and MGD effectively transfer knowledge from the teacher to the student model. Our experiments, conducted on a real-world dataset comprising sugar beet crops and four weed types (Cirsium, Convolvulus, Fallopia, and Echinochloa), consistently show increased AP50 across all classes. The distilled CWD student model achieves a notable improvement of 2.5% and MGD achieves 1.9% in mAP50 over the baseline without increasing model complexity. Additionally, we validate real-time deployment feasibility by evaluating the student YOLO11n model on Jetson Orin Nano and Raspberry Pi 5 embedded devices, performing five independent runs to evaluate performance stability across random seeds. These findings confirm CWD and MGD as an effective, efficient, and practical approach for improving deep learning-based weed detection accuracy in precision agriculture and plant phenotyping scenarios.

Related papers

• Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout [62.73150122809138]
  Federated Learning (FL) is a promising distributed machine learning approach that enables collaborative training of a global model using multiple edge devices.<n>We propose the FedDHAD FL framework, which comes with two novel methods: Dynamic Heterogeneous model aggregation (FedDH) and Adaptive Dropout (FedAD)<n>The combination of these two methods makes FedDHAD significantly outperform state-of-the-art solutions in terms of accuracy (up to 6.7% higher), efficiency (up to 2.02 times faster), and cost (up to 15.0% smaller)
  arXiv  Detail & Related papers  (2025-07-14T16:19:00Z)
• Robotic System with AI for Real Time Weed Detection, Canopy Aware Spraying, and Droplet Pattern Evaluation [0.0]
  We develop a vision guided, AI-driven variable rate sprayer system capable of detecting weed presence, estimating canopy size, and dynamically adjusting nozzle activation in real time.<n>The system integrates lightweight YOLO11n and YOLO11n-seg deep learning models, deployed on an NVIDIA Jetson Orin Nano for onboard inference.<n>Future work will focus on expanding the detection capabilities to include three common weed species in South Dakota.
  arXiv  Detail & Related papers  (2025-07-07T19:27:29Z)
• Involution-Infused DenseNet with Two-Step Compression for Resource-Efficient Plant Disease Classification [0.0]
  This study proposes a two-step model compression approach integrating Weight Pruning and Knowledge Distillation.<n>The results demonstrate ResNet50s superior performance post-compression, achieving 99.55% and 98.99% accuracy on the PlantVillage and PaddyLeaf datasets.
  arXiv  Detail & Related papers  (2025-05-31T22:43:23Z)
• Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation [53.30082523545212]
  Knowledge distillation (KD) is a core component in the training and deployment of modern generative models.<n>We show that KD induces a trade-off between precision and recall in the student model.<n>Our analysis provides a simple and general explanation for the effectiveness of KD in generative modeling.
  arXiv  Detail & Related papers  (2025-05-19T13:39:47Z)
• Exploring Model Quantization in GenAI-based Image Inpainting and Detection of Arable Plants [0.0]
  We propose a framework that leverages Stable Diffusion-based inpainting to augment training data progressively in 10% increments -- up to an additional 200%.<n>Our approach is evaluated on two state-of-the-art object detection models, YOLO11(l) and RT-DETR(l), using the mAP50 metric to assess detection performance.<n> Deployment of the downstream models on the Jetson Orin Nano demonstrates the practical viability of our framework in resource-constrained environments.
  arXiv  Detail & Related papers  (2025-03-04T09:05:01Z)
• Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data [51.745219224707384]
  Graph Neural Networks (GNNs) have achieved remarkable performance through their message-passing mechanism.<n>Recent studies have highlighted the vulnerability of GNNs to backdoor attacks.<n>In this paper, we propose a practical backdoor mitigation framework, denoted as GRAPHNAD.
  arXiv  Detail & Related papers  (2025-01-10T10:16:35Z)
• Comparative Analysis of YOLOv9, YOLOv10 and RT-DETR for Real-Time Weed Detection [0.0]
  This paper presents a comprehensive evaluation of object detection models, including YOLOv9, YOLOv10, and RT-DETR, for weed detection in smart-spraying applications.<n>The performance of these models is compared based on mean Average Precision (mAP) scores and inference times on different GPU and CPU devices.
  arXiv  Detail & Related papers  (2024-12-18T04:15:32Z)
• Enhancing weed detection performance by means of GenAI-based image augmentation [0.0]
  This paper investigates a generative AI-based augmentation technique that uses the Stable Diffusion model to produce diverse synthetic images for weed detection models.<n>Results show substantial improvements in mean Average Precision for YOLO models trained with generative AI-augmented datasets.
  arXiv  Detail & Related papers  (2024-11-27T17:00:34Z)
• Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation [56.053397775016755]
  We propose a sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student. To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students.
  arXiv  Detail & Related papers  (2023-08-17T17:17:08Z)
• Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in Orchards [68.95806641664713]
  We explore the usability of Stable Diffusion 2.1-base for generating synthetic datasets of apple trees for object detection. We train a YOLOv5m object detection model to predict apples in a real-world apple detection dataset. Results demonstrate that the model trained on generated data is slightly underperforming compared to a baseline model trained on real-world images.
  arXiv  Detail & Related papers  (2023-06-20T09:46:01Z)
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation [65.62538699160085]
  We propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments.
  arXiv  Detail & Related papers  (2022-11-21T03:09:42Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.