iNatAg: Multi-Class Classification Models Enabled by a Large-Scale Benchmark Dataset with 4.7M Images of 2,959 Crop and Weed Species

2025-03-25

AI Summary

Accurate crop-weed discrimination faces challenges including high inter-species visual similarity, strong environmental interference, and scarcity of large-scale, fine-grained agricultural image data. To address these, we introduce iNatAg—the first globally representative, fine-grained agricultural benchmark dataset comprising 4.7 million images across 2,959 species. We propose an agriculture-specific multi-granularity annotation scheme: binary crop/weed classification coupled with hierarchical taxonomic classification (family, genus, species), and pioneer the integration of geospatial metadata with LoRA-based efficient fine-tuning. Leveraging Swin Transformer, we design a novel multi-task learning framework incorporating geographic embeddings. Our model achieves 92.38% accuracy on crop-weed binary classification, establishing a new state-of-the-art. The iNatAg dataset is publicly released on the AgML platform to support agricultural AI development and misclassification root-cause analysis.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate identification of crop and weed species is critical for precision agriculture and sustainable farming. However, it remains a challenging task due to a variety of factors -- a high degree of visual similarity among species, environmental variability, and a continued lack of large, agriculture-specific image data. We introduce iNatAg, a large-scale image dataset which contains over 4.7 million images of 2,959 distinct crop and weed species, with precise annotations along the taxonomic hierarchy from binary crop/weed labels to specific species labels. Curated from the broader iNaturalist database, iNatAg contains data from every continent and accurately reflects the variability of natural image captures and environments. Enabled by this data, we train benchmark models built upon the Swin Transformer architecture and evaluate the impact of various modifications such as the incorporation of geospatial data and LoRA finetuning. Our best models achieve state-of-the-art performance across all taxonomic classification tasks, achieving 92.38% on crop and weed classification. Furthermore, the scale of our dataset enables us to explore incorrect misclassifications and unlock new analytic possiblities for plant species. By combining large-scale species coverage, multi-task labels, and geographic diversity, iNatAg provides a new foundation for building robust, geolocation-aware agricultural classification systems. We release the iNatAg dataset publicly through AgML (https://github.com/Project-AgML/AgML), enabling direct access and integration into agricultural machine learning workflows.

Problem

• Accurate identification of crop and weed species for precision agriculture
• Addressing lack of large agriculture-specific image datasets
• Improving classification models with geospatial data and LoRA finetuning

Innovation

• Large-scale dataset with 4.7M images
• Swin Transformer architecture models
• Geospatial data and LoRA finetuning