In this paper, we show our solution to the Google Landmark Recognition 2021 Competition. Firstly, embeddings of images are extracted via various architectures (i.e. CNN-, Transformer- and hybrid-based), which are optimized by ArcFace loss. Then we apply an efficient pipeline to re-rank predictions by adjusting the retrieval score with classification logits and non-landmark distractors. Finally, the ensembled model scores 0.489 on the private leaderboard, achieving the 3rd place in the 2021 edition of the Google Landmark Recognition Competition.
@article{arxiv.2110.02794,
title = {3rd Place Solution to Google Landmark Recognition Competition 2021},
author = {Cheng Xu and Weimin Wang and Shuai Liu and Yong Wang and Yuxiang Tang and Tianling Bian and Yanyu Yan and Qi She and Cheng Yang},
journal= {arXiv preprint arXiv:2110.02794},
year = {2021}
}