Google Landmark Retrieval 2021 Competition Third Place Solution

Abstract

We present our solutions to the Google Landmark Challenges 2021, for both the retrieval and the recognition tracks. Both solutions are ensembles of transformers and ConvNet models based on Sub-center ArcFace with dynamic margins. Since the two tracks share the same training data, we used the same pipeline and training approach, but with different model selections for the ensemble and different post-processing. The key improvement over last year is newer state-of-the-art vision architectures, especially transformers which significantly outperform ConvNets for the retrieval task. We finished third and fourth places for the retrieval and recognition tracks respectively.

References in corpus (8)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• EfficientNetV2: Smaller Models and Faster Training
• Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset
• Google Landmark Recognition 2020 Competition Third Place Solution
• Team JL Solution to Google Landmark Recognition 2019
• 1st Place Solution to Google Landmark Retrieval 2020
• Supporting large-scale image recognition with out-of-domain samples
• Towards A Fairer Landmark Recognition Dataset