# Improving Food Image Recognition with Noisy Vision Transformer

arXiv: https://arxiv.org/abs/2503.18997 · HTML: https://mlsanity.com/paper/2503.18997/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning](https://mlsanity.com/paper/2402.15761/) (2024)
- [FoodSAM: Any Food Segmentation](https://mlsanity.com/paper/2308.05938/) (2023)
- [NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems](https://mlsanity.com/paper/2309.10625/) (2023)
- [Improving Food Detection For Images From a Wearable Egocentric Camera](https://mlsanity.com/paper/2301.07861/) (2023)

## Built on by (most cited first, 1 of 1)

- [FoodCHA: Multi-Modal LLM Agent for Fine-Grained Food Analysis](https://mlsanity.com/paper/2605.05499/) (2026)

## Abstract (arXiv)

Food image recognition is a challenging task in computer vision due to the high variability and complexity of food images. In this study, we investigate the potential of Noisy Vision Transformers (NoisyViT) for improving food classification performance. By introducing noise into the learning process, NoisyViT reduces task complexity and adjusts the entropy of the system, leading to enhanced model accuracy. We fine-tune NoisyViT on three benchmark datasets: Food2K (2,000 categories, ~1M images), Food-101 (101 categories, ~100K images), and CNFOOD-241 (241 categories, ~190K images). The performance of NoisyViT is evaluated against state-of-the-art food recognition models. Our results demonstrate that NoisyViT achieves Top-1 accuracies of 95%, 99.5%, and 96.6% on Food2K, Food-101, and CNFOOD-241, respectively, significantly outperforming existing approaches. This study underscores the potential of NoisyViT for dietary assessment, nutritional monitoring, and healthcare applications, paving the way for future advancements in vision-based food computing. Code for reproducing NoisyViT for food recognition is available at NoisyViT_Food.