# 2nd Place Solution to Google Universal Image Embedding

Source: [2nd Place Solution to Google Universal Image Embedding](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b445>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:40:22.216Z

Authors: Xiaolong Huang, Qiankun Li

Published: 2022-10-17T04:04:16.000Z

## Abstract

Image representations are a critical building block of computer vision applications. This paper presents the 2nd place solution to the Google Universal Image Embedding Competition, which is part of the ECCV2022 instance-level recognition workshops. We use the instance-level fine-grained image classification method to complete this competition. We focus on data building and processing, model structure, and training strategies. Finally, the solution scored 0.713 on the public leaderboard and 0.709 on the private leaderboard.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.08735>)

[PDF](<https://arxiv.org/pdf/2210.08735.pdf>)