mlsanityData to 7 Oct 2026

Google Landmark Recognition 2020 Competition Third Place Solution

arXiv 2010.05350 ↗First posted 11 Oct 2020cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

We present our third place solution to the Google Landmark Recognition 2020 competition. It is an ensemble of global features only Sub-center ArcFace models. We introduce dynamic margins for ArcFace loss, a family of tune-able margin functions of class size, designed to deal with the extreme imbalance in GLDv2 dataset. Progressive finetuning and careful postprocessing are also key to the solution. Our two submissions scored 0.6344 and 0.6289 on private leaderboard, both ranking third place out of 736 teams.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 4; 2023: 0; 2024: 1; 2025: 1.

9 papers.

  1. 20221st Place Solution in Google Universal Images Embeddingcited by 10
  2. 2022EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud Computingcited by 5
  3. 2021Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformerscited by 3
  4. 2022ScaleFace: Uncertainty-aware Deep Metric Learningcited by 3
  5. 20213rd Place Solution to Google Landmark Recognition Competition 2021cited by 2
  6. 20226th Place Solution to Google Universal Image Embeddingcited by 1
  7. 2024Efficient and Discriminative Image Feature Extraction for Universal Image Retrievalcited by 1
  8. 2025Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Successcited by 1
  9. 2021Google Landmark Retrieval 2021 Competition Third Place Solutioncited by 0