Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908625230888960 |
|---|---|
| author | Jain, Riddhi Patwardhan, Manasi Mishra, Aayush Deshpande, Parijat Rai, Beena |
| author_facet | Jain, Riddhi Patwardhan, Manasi Mishra, Aayush Deshpande, Parijat Rai, Beena |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01449 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction Jain, Riddhi Patwardhan, Manasi Mishra, Aayush Deshpande, Parijat Rai, Beena Computer Vision and Pattern Recognition Artificial Intelligence 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 |
| title | Privacy Preserving Ordinal-Meta Learning with VLMs for Fine-Grained Fruit Quality Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.01449 |