Deep semi-supervised approach based on consistency regularization and similarity learning for weeds classification

2025-10-12

AI Summary

Weed-crop morphological similarity, highly variable field conditions, and severe scarcity of labeled data critically hinder the application of deep learning to precision agriculture weed identification. To address these challenges, we propose a semi-supervised classification framework based on deep autoencoders, which innovatively integrates consistency regularization with similarity learning to effectively leverage unlabeled data and enhance model robustness and generalization. Our method significantly outperforms fully supervised baselines under extremely low labeling rates (e.g., 10% labeled samples), achieving superior accuracy on the DeepWeeds benchmark while demonstrating strong resilience to image noise. Ablation studies systematically validate the contribution of each component. The proposed approach establishes an efficient, practical paradigm for weed recognition in resource-constrained agricultural settings, advancing semi-supervised learning for real-world agri-vision applications.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Weed species classification represents an important step for the development of automated targeting systems that allow the adoption of precision agriculture practices. To reduce costs and yield losses caused by their presence. The identification of weeds is a challenging problem due to their shared similarities with crop plants and the variability related to the differences in terms of their types. Along with the variations in relation to changes in field conditions. Moreover, to fully benefit from deep learning-based methods, large fully annotated datasets are needed. This requires time intensive and laborious process for data labeling, which represents a limitation in agricultural applications. Hence, for the aim of improving the utilization of the unlabeled data, regarding conditions of scarcity in terms of the labeled data available during the learning phase and provide robust and high classification performance. We propose a deep semi-supervised approach, that combines consistency regularization with similarity learning. Through our developed deep auto-encoder architecture, experiments realized on the DeepWeeds dataset and inference in noisy conditions demonstrated the effectiveness and robustness of our method in comparison to state-of-the-art fully supervised deep learning models. Furthermore, we carried out ablation studies for an extended analysis of our proposed joint learning strategy.

Problem

• Classifying weed species using limited labeled data for precision agriculture
• Addressing visual similarities between weeds and crops under field variations
• Reducing dependency on large annotated datasets through semi-supervised learning

Innovation

• Deep semi-supervised learning for weed classification
• Combines consistency regularization with similarity learning
• Uses deep auto-encoder architecture for robust performance