3rd Place Solution to Large-scale Fine-grained Food Recognition

TL;DR

This paper presents a winning third-place solution for a large-scale fine-grained food recognition challenge, utilizing a combination of Arcface and Circle loss functions, with model ensembling for improved accuracy.

Contribution

The paper introduces a novel combination of Arcface and Circle loss functions for fine-grained food recognition, achieving competitive results in a Kaggle challenge.

Findings

Combination of Arcface and Circle loss improves performance.

Careful tuning and ensembling lead to top-tier results.

Achieved third place in the competition.

Abstract

Food analysis is becoming a hot topic in health area, in which fine-grained food recognition task plays an important role. In this paper, we describe the details of our solution to the LargeFineFoodAI-ICCV Workshop-Recognition challenge held on Kaggle. We find a proper combination of Arcface loss[1] and Circle loss[9] can bring improvement to the performance. With Arcface and the combined loss, model was trained with carefully tuned configurations and ensembled to get the final results. Our solution won the 3rd place in the competition.