通过引入噪声提升视觉变压器，显著改善食物图像识别准确率。
Improving Food Image Recognition with Noisy Vision Transformer
- 在训练中加入噪声，降低任务复杂度并优化模型熵
- 在三大数据集上分别达到95%、99.5%、96.6%的准确率
- 适合营养监测与医疗健康领域的视觉食物分析应用
食物图像识别因食物形态和光照变化大而极具挑战。本文研究了噪声视觉变压器（NoisyViT）在提升食物分类性能方面的潜力。通过在学习过程中引入噪声，NoisyViT降低了任务复杂度并调节系统熵，从而提升模型精度。我们在三个基准数据集上微调NoisyViT：Food2K（2000类，约100万张图像）、Food-101（101类，约10万张图像）和CNFOOD-241（241类，约19万张图像）。实验结果表明，NoisyViT在Food2K、Food-101和CNFOOD-241上的Top-1准确率分别达到95%、99.5%和96.6%，显著优于现有方法。本研究凸显了NoisyViT在膳食评估、营养监测和医疗健康中的应用前景，为基于视觉的食物计算技术发展提供新方向。代码已公开于NoisyViT_Food。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。