1st Place Solution to Google Landmark Retrieval 2020

TL;DR

This paper details the winning approach to the Google Landmark Retrieval 2020 challenge, utilizing advanced metric learning, transfer learning, and ensemble techniques to achieve top performance in landmark image retrieval.

Contribution

It introduces a novel combination of metric learning, transfer learning, and ensemble methods specifically tailored for large-scale landmark retrieval tasks.

Findings

Achieved 0.38677 mAP@100 on private leaderboard.

Demonstrated the effectiveness of transfer learning and ensemble techniques.

Improved landmark retrieval accuracy over previous methods.

Abstract

This paper presents the 1st place solution to the Google Landmark Retrieval 2020 Competition on Kaggle. The solution is based on metric learning to classify numerous landmark classes, and uses transfer learning with two train datasets, fine-tuning on bigger images, adjusting loss weight for cleaner samples, and esemble to enhance the model's performance further. Finally, it scored 0.38677 mAP@100 on the private leaderboard.