Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction

TL;DR

This paper presents MAOML, a meta-learning approach that enhances open-source Vision Language Models for fine-grained fruit freshness prediction, achieving state-of-the-art accuracy while preserving data privacy.

Contribution

Introduces a novel Model-Agnostic Ordinal Meta-Learning algorithm to improve open-source VLMs for fruit freshness classification under limited data conditions.

Findings

Achieves 92.71% accuracy in fruit freshness prediction.

Outperforms existing open-source VLMs in zero-shot and few-shot settings.

Demonstrates effective privacy-preserving fruit quality assessment.

Abstract

To effectively manage the wastage of perishable fruits, it is crucial to accurately predict their freshness or shelf life using non-invasive methods that rely on visual data. In this regard, deep learning techniques can offer a viable solution. However, obtaining fine-grained fruit freshness labels from experts is costly, leading to a scarcity of data. Closed proprietary Vision Language Models (VLMs), such as Gemini, have demonstrated strong performance in fruit freshness detection task in both zero-shot and few-shot settings. Nonetheless, food retail organizations are unable to utilize these proprietary models due to concerns related to data privacy, while existing open-source VLMs yield sub-optimal performance for the task. Fine-tuning these open-source models with limited data fails to achieve the performance levels of proprietary models. In this work, we introduce a Model-Agnostic Ordinal Meta-Learning (MAOML) algorithm, designed to train smaller VLMs. This approach utilizes meta-learning to address data sparsity and leverages label ordinality, thereby achieving state-of-the-art performance in the fruit freshness classification task under both zero-shot and few-shot settings. Our method achieves an industry-standard accuracy of 92.71%, averaged across all fruits. Keywords: Fruit Quality Prediction, Vision Language Models, Meta Learning, Ordinal Regression