mlsanityData to 14 Oct 2026

WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classification

arXiv 2505.18930 ↗First posted 25 May 2025cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Early weed identification is crucial for effective management and control, and researchers, agronomists, and technology developers are increasingly interested in automating this process using computer vision and artificial intelligence; however, limited expert-verified data and variable morphological features have hindered the development of AI-based weed identification models. To address these issues, we present WeedNet, a global-scale weed identification model that can recognize an extensive set of weed species. WeedNet is an end-to-end real-time weed identification pipeline that uses self-supervised learning, fine-tuning, and enhanced trustworthiness strategies. WeedNet achieved 91.02% accuracy across 1,593 weed species, with 41% of species achieving 100% accuracy. Using a fine-tuning approach, the local Iowa WeedNet model achieved 97.38% overall accuracy for 84 Iowa weeds. Testing across intra-species dissimilarity and inter-species similarity suggests that diversity in the collected image, spanning all growth stages and distinct plant characteristics, is crucial to driving model performance. The global WeedNet model serves as a foundation, and the global-to-local strategy enables targeted fine-tuning to improve performance in regional weed communities. Additional validation of drone- and ground-rover-based images highlights WeedNet's potential for integration into robotic platforms. Furthermore, integration with artificial intelligence for conversational use provides intelligent agricultural and ecological conservation consulting tools for farmers, researchers, and government agencies across diverse landscapes.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 48 of its 152 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

48 of 152 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  12. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
36 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  2. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  3. 2021Transformers in Vision: A Surveycited by 1,013
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  6. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  7. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  10. 2022Multimodal Learning with Transformers: A Surveycited by 400
  11. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  12. 2021Benchmarking Representation Learning for Natural World Image Collectionscited by 168
  13. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 152
  14. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  15. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  16. 2022OmniMAE: Single Model Masked Pretraining on Images and Videoscited by 99
  17. 2018DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learningcited by 69
  18. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  19. 2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
  20. 2023The effectiveness of MAE pre-pretraining for billion-scale pretrainingcited by 68
  21. 2020Masked Face Recognition Dataset and Applicationcited by 66
  22. 2023Spatial Implicit Neural Representations for Global-Scale Species Mappingcited by 59
  23. 2020Methods for Pruning Deep Neural Networkscited by 49
  24. 2019Geo-Aware Networks for Fine-Grained Recognitioncited by 44
  25. 2021A Survey of Deep Learning Techniques for Weed Detection from Imagescited by 23
  26. 2017A Public Image Database for Benchmark of Plant Seedling Classification Algorithmscited by 20
  27. 2021Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systemscited by 15
  28. 2018A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretabilitycited by 8
  29. 2023Deep learning powered real-time identification of insects using citizen science datacited by 8
  30. 2023Out-of-distribution detection algorithms for robust insect classificationcited by 7
  31. 2022From Explanations to Segmentation: Using Explainable AI for Image Segmentationcited by 5
  32. 2023Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthinesscited by 4
  33. 2025iNatAg: Multi-Class Classification Models Enabled by a Large-Scale Benchmark Dataset with 4.7M Images of 2,959 Crop and Weed Speciescited by 3
  34. 2020How useful is Active Learning for Image-based Plant Phenotyping?cited by 2
  35. 2025WeedVision: Multi-Stage Growth and Classification of Weeds using DETR and RetinaNet for Precision Agriculturecited by 2
  36. 2021Deep-CNN based Robotic Multi-Class Under-Canopy Weed Control in Precision Farmingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotypingcited by 1
  2. 2025Advancements in Weed Mapping: A Systematic Reviewcited by 0
  3. 2026Self-supervised training for high-resolution close-range multispectral remote sensing imagerycited by 0
  4. 2026AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretrainingcited by 0