Energy-Efficient Plant Monitoring via Knowledge Distillation

TL;DR

This paper demonstrates that knowledge distillation can produce smaller, efficient plant recognition models that maintain high accuracy, enabling deployment in resource-limited environments like mobile devices.

Contribution

The study provides an extensive empirical evaluation of knowledge distillation for plant recognition, showing consistent performance improvements across multiple architectures and training regimes.

Findings

Distilled models match larger models' performance with lower computational cost.

Knowledge distillation improves accuracy across all tested architectures.

70 models were trained and evaluated on two challenging benchmarks.

Abstract

Recent advances in large-scale visual representation learning have significantly improved performance in plant species and plant disease recognition tasks. However, state-of-the-art models, often based on high-capacity vision transformers or multimodal foundation models, remain computationally expensive and difficult to deploy in resource-constrained environments such as mobile or edge devices. This limitation hinders the scalability of automated biodiversity monitoring and precision agriculture systems, where efficiency is as critical as accuracy. In this work, we investigate knowledge distillation as an effective approach to transfer the representational capacity of large pretrained models into smaller, more efficient architectures. We focus on plant species and disease recognition, and conduct an extensive empirical study on two challenging benchmarks: Pl@ntNet300K-v2 and Deep-Plant-Disease. We evaluate four representative architectures, including two ConvNeXt models and two vision transformers, under multiple training regimes: from-scratch training and pretrained initialization, each with and without distillation. In total, we train and evaluate 70 models. Our results show that knowledge distillation consistently improves performance across tasks and architectures. Distilled models are able to match the performance of significantly larger models while maintaining substantially lower computational cost. These findings demonstrate the potential of knowledge distillation techniques to enable efficient and scalable deployment of plant recognition systems in real-world environmental applications.