# 2nd Place Solution to Google Landmark Recognition Competition 2021

arXiv: https://arxiv.org/abs/2110.02638 · HTML: https://mlsanity.com/paper/2110.02638/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset](https://mlsanity.com/paper/1906.04087/) (2019)
- [Attention-Aware Generalized Mean Pooling for Image Retrieval](https://mlsanity.com/paper/1811.00202/) (2018)
- [1st Place Solution to Google Landmark Retrieval 2020](https://mlsanity.com/paper/2009.05132/) (2020)
- [Team JL Solution to Google Landmark Recognition 2019](https://mlsanity.com/paper/1906.11874/) (2019)
- [2nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019](https://mlsanity.com/paper/1906.03990/) (2019)

## Built on by (most cited first, 1 of 1)

- [Google Landmark Retrieval 2021 Competition Third Place Solution](https://mlsanity.com/paper/2110.04619/) (2021)

## Abstract (arXiv)

As Transformer-based architectures have recently shown encouraging progresses in computer vision. In this work, we present the solution to the Google Landmark Recognition 2021 Challenge held on Kaggle, which is an improvement on our last year's solution by changing three designs, including (1) Using Swin and CSWin as backbone for feature extraction, (2) Train on full GLDv2, and (3) Using full GLDv2 images as index image set for kNN search. With these modifications, our solution significantly improves last year solution on this year competition. Our full pipeline, after ensembling Swin, CSWin, EfficientNet B7 models, scores 0.4907 on the private leaderboard which help us to get the 2nd place in the competition.