3rd Place Solution to Google Landmark Recognition Competition 2021
Not on the map. Why?
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.
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
11 of 14 references.
References · 11
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
- 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
- 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
- 2018Attention-Aware Generalized Mean Pooling for Image Retrievalcited by 12
- 2020Supporting large-scale image recognition with out-of-domain samplescited by 9
- 2020Google Landmark Recognition 2020 Competition Third Place Solutioncited by 9
- 2021Towards A Fairer Landmark Recognition Datasetcited by 9
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.