# 3rd Place Solution to Google Landmark Recognition Competition 2021

arXiv: https://arxiv.org/abs/2110.02794 · HTML: https://mlsanity.com/paper/2110.02794/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 11 of 11)

- [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)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Attention-Aware Generalized Mean Pooling for Image Retrieval](https://mlsanity.com/paper/1811.00202/) (2018)
- [Supporting large-scale image recognition with out-of-domain samples](https://mlsanity.com/paper/2010.01650/) (2020)
- [Google Landmark Recognition 2020 Competition Third Place Solution](https://mlsanity.com/paper/2010.05350/) (2020)
- [Towards A Fairer Landmark Recognition Dataset](https://mlsanity.com/paper/2108.08874/) (2021)

## Built on by (most cited first, 2 of 2)

- [Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval](https://mlsanity.com/paper/2305.02610/) (2023)
- [Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning](https://mlsanity.com/paper/2503.14824/) (2025)

## Abstract (arXiv)

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.