Meta-learning improves plant growth estimates with few labels
Meta-Learning for Data-Efficient Plant Growth Estimation via Vision Transformers and Fuzzy Clustering
Computer Vision and Pattern RecognitionMachine Learning
Summary
Measuring how plants grow in greenhouses is important but getting enough labeled pictures for machine learning is hard and expensive. This paper shows how a special kind of AI called meta-learning can learn from just a few labeled images by grouping many unlabeled images into tasks using fuzzy clustering. They use Vision Transformers to understand the images better and train models that quickly adapt to new tasks with little data. Their tests on two plant image sets show this method estimates growth accurately even when labeled data is very limited.
What this means in practice
- •For greenhouse operators: Estimate plant growth accurately with minimal labeled images using meta-learning models trained on clustered unlabeled data.
- •For agricultural technology developers: Develop plant monitoring tools that learn from few labeled samples by organizing visual data into tasks and using vision transformer embeddings.
Authors
Sheikh Hasan Elahi, Rusith Chamara Hathurusinghe Dewage, Habib Ullah, Muhammad Salman Siddiqui, Rakibul Islam, Fadi Al Machot
Abstract
Accurate plant growth estimation is essential for greenhouse monitoring, yet obtaining labeled data remains costly and time-consuming. To address this, we propose a few-shot regression framework that combines Vision Transformer (ViT) feature embeddings, clustering-based task construction, and gradient-based meta-learning, and show that task construction in embedding space is a primary driver of performance. The approach leverages an unlabeled image pool to organize data into structured tasks using fuzzy c-means clustering, enabling efficient learning from a small number of labeled samples. We systematically evaluate meta-learning methods and show that second-order methods (e.g., Model-Agnostic Meta-Learning variants such as MAML++) outperform classical baselines in the few-shot regime. Furthermore, intra-cluster support selection has a limited and dataset-dependent impact. Experiments on two plant datasets show that structured task design combined with meta-learning enables reliable plant growth estimation under severe label scarcity.