# Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval

arXiv: https://arxiv.org/abs/2003.11211 · HTML: https://mlsanity.com/paper/2003.11211/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 18 of 18)

- [Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities](https://mlsanity.com/paper/2302.11154/) (2023)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Learning Super-Features for Image Retrieval](https://mlsanity.com/paper/2201.13182/) (2022)
- [Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection](https://mlsanity.com/paper/2112.04323/) (2021)
- [Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation](https://mlsanity.com/paper/2105.07645/) (2021)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [PP-ShiTu: A Practical Lightweight Image Recognition System](https://mlsanity.com/paper/2111.00775/) (2021)
- [Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information](https://mlsanity.com/paper/2206.01326/) (2022)
- [Content-Based Landmark Retrieval Combining Global and Local Features using Siamese Neural Networks](https://mlsanity.com/paper/2208.04201/) (2022)
- [MABNet: Master Assistant Buddy Network with Hybrid Learning for Image Retrieval](https://mlsanity.com/paper/2303.03050/) (2023)
- [XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge](https://mlsanity.com/paper/2307.11317/) (2023)
- [Retrieval Robust to Object Motion Blur](https://mlsanity.com/paper/2404.18025/) (2024)
- [AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval](https://mlsanity.com/paper/2405.17718/) (2024)
- [MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding](https://mlsanity.com/paper/2512.17492/) (2025)

## Abstract (arXiv)

We propose an efficient pipeline for large-scale landmark image retrieval that addresses the diversity of the dataset through two-stage discriminative re-ranking. Our approach is based on embedding the images in a feature-space using a convolutional neural network trained with a cosine softmax loss. Due to the variance of the images, which include extreme viewpoint changes such as having to retrieve images of the exterior of a landmark from images of the interior, this is very challenging for approaches based exclusively on visual similarity. Our proposed re-ranking approach improves the results in two steps: in the sort-step, k-nearest neighbor search with soft-voting to sort the retrieved results based on their label similarity to the query images, and in the insert-step, we add additional samples from the dataset that were not retrieved by image-similarity. This approach allows overcoming the low visual diversity in retrieved images. In-depth experimental results show that the proposed approach significantly outperforms existing approaches on the challenging Google Landmarks Datasets. Using our methods, we achieved 1st place in the Google Landmark Retrieval 2019 challenge and 3rd place in the Google Landmark Recognition 2019 challenge on Kaggle. Our code is publicly available here: urlhttps://github.com/lyakaap/Landmark2019-1st-and-3rd-Place-Solution