3rd Place Solution to "Google Landmark Retrieval 2020"

08/24/2020
by   Ke Mei, et al.
13

Image retrieval is a fundamental problem in computer vision. This paper presents our 3rd place detailed solution to the Google Landmark Retrieval 2020 challenge. We focus on the exploration of data cleaning and models with metric learning. We use a data cleaning strategy based on embedding clustering. Besides, we employ a data augmentation method called Corner-Cutmix, which improves the model's ability to recognize multi-scale and occluded landmark images. We show in detail the ablation experiments and results of our method.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset