Single-Stage Heavy-Tailed Food Classification

TL;DR

This paper introduces a novel single-stage deep learning framework for food classification that effectively handles heavy-tailed data distributions, improving accuracy on benchmark datasets by over 5%.

Contribution

It presents a new single-stage approach specifically designed to address class imbalance in heavy-tailed food image datasets.

Findings

Achieves over 5% improvement in top-1 accuracy on Food101-LT and VFN-LT datasets.

Effectively mitigates class imbalance issues in heavy-tailed food image data.

Outperforms existing methods on benchmark datasets.

Abstract

Deep learning based food image classification has enabled more accurate nutrition content analysis for image-based dietary assessment by predicting the types of food in eating occasion images. However, there are two major obstacles to apply food classification in real life applications. First, real life food images are usually heavy-tailed distributed, resulting in severe class-imbalance issue. Second, it is challenging to train a single-stage (i.e. end-to-end) framework under heavy-tailed data distribution, which cause the over-predictions towards head classes with rich instances and under-predictions towards tail classes with rare instance. In this work, we address both issues by introducing a novel single-stage heavy-tailed food classification framework. Our method is evaluated on two heavy-tailed food benchmark datasets, Food101-LT and VFN-LT, and achieves the best performance compared to existing work with over 5% improvements for top-1 accuracy.