2nd Place Solution to Google Landmark Recognition Competition 2021
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 6 Oct 2021.
Builds on
10 of 12 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
- 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
- 2019Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Datasetcited by 17
- 2018Attention-Aware Generalized Mean Pooling for Image Retrievalcited by 12
- 20201st Place Solution to Google Landmark Retrieval 2020cited by 6
- 2019Team JL Solution to Google Landmark Recognition 2019cited by 2
- 20192nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019cited by 1
Built on by
Citing papers per year: 2021: 1.
1 paper.