3rd Place Solution to ICCV LargeFineFoodAI Retrieval

Yang Zhong, Zhiming Wang, Zhaoyang Li, Jinyu Ma, Xiang Li
10/24/2025
cs.CV

No confident code implementation found for this paper.

Abstract

This paper introduces the 3rd place solution to the ICCV LargeFineFoodAI Retrieval Competition on Kaggle. Four basic models are independently trained with the weighted sum of ArcFace and Circle loss, then TTA and Ensemble are successively applied to improve feature representation ability. In addition, a new reranking method for retrieval is proposed based on diffusion and k-reciprocal reranking. Finally, our method scored 0.81219 and 0.81191 mAP@100 on the public and private leaderboard, respectively.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Guiding Retrieval using LLM-based Listwise Rankers

83% match1 repo32025

Global Features are All You Need for Image Retrieval and Reranking

82% match1 repo2492026

rerankers: A Lightweight Python Library to Unify Ranking Methods

82% match1 repo1.6k2024

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

81% match2026

Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF

80% match2024

Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking

80% match2025

Cite this paper

@article{zhong2025place,
  title  = {3rd Place Solution to ICCV LargeFineFoodAI Retrieval},
  author = {Yang Zhong and Zhiming Wang and Zhaoyang Li and Jinyu Ma and Xiang Li},
  year   = {2025},
  eprint = {2510.21198},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.21198v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.21198.svg)](https://codeofpaper.com/paper/2510.21198)

Discussion