Feature-Enhanced TResNet for Fine-Grained Food Image Classification

TL;DR

This paper introduces FE-TResNet, a deep learning model that enhances fine-grained food image classification by integrating feature enhancement modules, achieving high accuracy on Chinese food datasets for improved dietary monitoring.

Contribution

The paper proposes FE-TResNet, a novel architecture with StyleRM and DCA modules, specifically designed to improve subtle feature recognition in fine-grained food image classification.

Findings

Achieved 81.37% accuracy on ChineseFoodNet

Achieved 80.29% accuracy on CNFOOD-241

Demonstrated effectiveness for dietary assessment

Abstract

Food is not only essential to human health but also serves as a medium for cultural identity and emotional connection. In the context of precision nutrition, accurately identifying and classifying food images is critical for dietary monitoring, nutrient estimation, and personalized health management. However, fine-grained food classification remains challenging due to the subtle visual differences among similar dishes. To address this, we propose Feature-Enhanced TResNet (FE-TResNet), a novel deep learning model designed to improve the accuracy of food image recognition in fine-grained scenarios. Built on the TResNet architecture, FE-TResNet integrates a Style-based Recalibration Module (StyleRM) and Deep Channel-wise Attention (DCA) to enhance feature extraction and emphasize subtle distinctions between food items. Evaluated on two benchmark Chinese food datasets-ChineseFoodNet and CNFOOD-241-FE-TResNet achieved high classification accuracies of 81.37% and 80.29%, respectively. These results demonstrate its effectiveness and highlight its potential as a key enabler for intelligent dietary assessment and personalized recommendations in precision nutrition systems.