PaperlayerView exact revision on arXiv

Source-linked AI summary

Meta-Learning for Data-Efficient Plant Growth Estimation via Vision Transformers and Fuzzy Clustering

Sheikh Hasan Elahi, Rusith Chamara Hathurusinghe Dewage, Habib Ullah, Muhammad Salman Siddiqui, Rakibul Islam, Fadi Al Machot

arXiv:2609.10749v1cs.CVcs.LG

TL;DR

Plant growth estimation requires efficient learning when greenhouse labels are costly and scarce. The paper combines ViT embeddings, fuzzy c-means task construction, and gradient-based meta-learning, finding that structured tasks and second-order methods support reliable few-shot regression while intra-cluster selection has limited, dataset-dependent effects.

Abstract

from arXiv · show

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.

I. INTRODUCTION

Plant growth estimation supports timely greenhouse management, but manual phenotyping and label-intensive deep learning limit high-frequency monitoring. The paper addresses this gap with few-shot meta-learning and embedding-space task construction.

  • Few-shot learning and meta-learning target plant phenotyping settings where labeled data are scarce and manual measurements are labor-intensive.Traditional measurements are reliable but unsuitable for high-frequency monitoring, while deep learning typically requires large labeled datasets.Source: §I · p. 1, A. Few-Shot Learning in Agriculture · p. 2
  • The proposed framework combines Vision Transformer embeddings, fuzzy c-means representative sampling, and gradient-based meta-learning for few-shot plant growth regression.Source: §I · p. 1
  • Clustering-based task construction organizes few-shot regression tasks in embedding space, while the study evaluates cross-dataset generalization on cucumber and lettuce.Source: §I · p. 1
  • The study reports that task construction dominates sampling heuristics and that second-order meta-learning is important for plant growth regression.Source: §I · p. 1
  • Structured sampling combined with meta-learning is presented as a practical solution for greenhouse phenotyping systems.Source: §I · p. 2

B. Meta-Learning for Low-Data Adaptation

The paper situates its approach at the intersection of meta-learning, Vision Transformer representations, and embedding-based sampling for agricultural few-shot tasks. It addresses the underexplored integration of representative sampling and meta-learning across plant species.

B. Meta-Learning for Low-Data Adaptation

C. Vision Transformers and Embedding-Based Sampling

  • The evaluation includes a cucumber dataset collected under controlled greenhouse conditions across 29 plants and 16 days of imaging.Source: A. NMBU Cucumber Dataset · p. 2

B. Competition Lettuce Dataset

The lettuce-dataset evaluation uses ViT embeddings, fuzzy c-means clustering, and gradient-based meta-learning to construct localized few-shot regression tasks. The dataset contains 388 annotated top-view lettuce images with canopy-width labels, while the proposed pipeline compares multiple meta-learning variants under a common setup.

B. Competition Lettuce Dataset

  • 388 top-view RGB lettuce images with canopy-width annotations are split into 310 training and 78 test images, producing 1,240 augmented training samples.The dataset represents a rosette structure distinct from cucumber.Source: B. Competition Lettuce Dataset · p. 2
  • The pipeline resizes plant images and extracts 768-dimensional embeddings with a pretrained ViT-Base/16 feature extractor.The embeddings are used to represent global morphological structure.Source: A. The Proposed Framework · p. 2
  • Fuzzy c-means organizes embeddings into morphologically coherent regions and supplies membership confidence for representative support selection.The number of clusters is selected on a validation set to avoid test-set leakage.Source: A. The Proposed Framework · p. 3
  • Each cluster defines a localized task with a representative support set and a query set sampled from remaining points assigned to that cluster.This construction is intended to expose the model to growth-pattern variation across plant structures.Source: A. The Proposed Framework · p. 3
  • The regression model is a two-layer MLP trained through task-based adaptation, with MAML, Meta-SGD, and MAML++ providing alternative gradient-based meta-learning procedures.MAML uses a fixed learning rate, Meta-SGD learns per-parameter rates, and MAML++ adds per-step learning rates and a multi-step meta-loss.Source: A. The Proposed Framework · p. 3
  • All methods share the same architecture and task construction, with validation-selected hyperparameters, multiple random seeds, and an 80:20 train/test split.Meta-training uses batches of tasks sampled from the cluster distribution.Source: A. The Proposed Framework · pp. 3–4

V. RESULTS

The evaluation uses held-out test sets over 20 random seeds, with standardized growth labels during training and millimeter-scale RMSE reporting. These choices define the protocol for comparing methods.

V. RESULTS

  • 20 random seeds are used to evaluate all methods on held-out test sets.Source: §V · p. 4
  • Growth labels are standardized during training and de-standardized for evaluation.Source: §V · p. 4
  • All RMSE values are reported in millimeters.Source: §V · p. 4

A. Main Performance Comparison

MAML++ achieves the strongest few-shot performance across cucumber and lettuce, reducing error toward full-data baselines while showing stable convergence across seeds.

B. Cluster Selection

Validation-based cluster selection identifies moderate granularity as effective for constructing few-shot tasks, with K = 7 performing best on both datasets.

  • K = 7 yields the lowest validation RMSE on both datasets, while performance remains stable between K = 7 and K = 10.Source: B. Cluster Selection · p. 5
  • Smaller cluster counts, including K = 3 and K = 5, generally produce higher error than the moderate-granularity settings.Source: B. Cluster Selection · p. 5
  • Cluster count is selected exclusively on a training-derived validation split, avoiding test-set leakage and supporting reproducible evaluation.Source: B. Cluster Selection · p. 5

C. Ablation of Within-Cluster Support Selection Strategies

Support-set coverage across clusters matters more than the specific representative-selection heuristic used within each cluster.

D. Statistical Significance

Statistical tests show that MAML systematically outperforms Reptile, while MAML++ offers a significant advantage over MAML on cucumber but not lettuce.

VI. DISCUSSION

The discussion finds that second-order meta-learning methods outperform first-order Reptile for few-shot plant growth regression, while MAML++ gains over MAML and representative sampling depend on the dataset.

  • Second-order methods show a large, statistically significant performance gap over first-order Reptile across both datasets.The discussion attributes this pattern to more precise parameter adaptation through inner-loop differentiation.Source: §VI · pp. 5–6
  • MAML++ achieves the best overall performance, but its advantage over MAML is substantial on cucumber and negligible on lettuce.The authors relate this dataset dependence to differences in dataset variability.Source: §VI · p. 6
  • Balanced sampling improves stability, whereas FCM-based representative sampling does not consistently outperform random selection.The reported pattern suggests that embedding-space coverage is more important than prototypicality.Source: §VI · p. 6
  • MAML++ reaches competitive performance using less than 6% of the augmented training data, with consistent trends across cucumber and lettuce.This supports the framework's relevance to settings with limited annotations and differing plant structures or imaging conditions.Source: §VI · p. 6

VII. CONCLUSION

The paper presents a data-efficient framework combining ViT representations, FCM-based task construction, and gradient-based meta-learning for few-shot plant growth estimation. Across cucumber and lettuce, MAML++ achieves the best overall performance, while structured representative sampling offers limited, dataset-dependent benefits.

  • MAML++ achieves the best overall few-shot performance, reaching 35.13 mm RMSE on cucumber and 29.13 mm on lettuce.Source: §VII · p. 6
  • The framework combines ViT-based representations, FCM-based task construction, and gradient-based meta-learning.Source: §VII · p. 6
  • The experiments show that second-order meta-learning is effective for low-data plant growth regression, while representative sampling benefits are limited and dataset-dependent.Source: §VII · p. 6
  • The study is limited to controlled greenhouse imagery and single-trait regression, with future work targeting broader crop diversity, temporal modeling, and uncertainty-aware prediction.Source: §VII · p. 6

Related papers

Loading 2609.10749v1…