EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition

Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a large database of geotagged photos, using learned global descriptors. A major challenge in this task is recognizing places seen from different viewpoints. To overcome this limitation, we propose a new method, called EigenPlaces, to train our neural network on images from different point of views, which embeds viewpoint robustness into the learned global descriptors. The underlying idea is to cluster the training data so as to explicitly present the model with different views of the same points of interest. The selection of this points of interest is done without the need for extra supervision. We then present experiments on the most comprehensive set of datasets in literature, finding that EigenPlaces is able to outperform previous state of the art on the majority of datasets, while requiring 60\% less GPU memory for training and using 50\% smaller descriptors. The code and trained models for EigenPlaces are available at {\small{\url{https://github.com/gmberton/EigenPlaces}}}, while results with any other baseline can be computed with the codebase at {\small{\url{https://github.com/gmberton/auto_VPR}}}.

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Place Recognition AmsterTime EigenPlaces Recall@1 48.9 # 1
Visual Place Recognition Eynsham EigenPlaces Recall@1 90.7 # 1
Visual Place Recognition Pittsburgh-250k-test EigenPlaces Recall@1 94.1 # 4
Visual Place Recognition Pittsburgh-30k-test EigenPlaces Recall@1 92.5 # 2
Visual Place Recognition San Francisco Landmark Dataset EigenPlaces Recall@1 89.6 # 1
Visual Place Recognition SF-XL test v1 EigenPlaces Recall@1 84.1 # 1
Visual Place Recognition SF-XL test v2 EigenPlaces Recall@1 90.8 # 2
Visual Place Recognition Tokyo247 EigenPlaces Recall@1 93 # 2

Methods


No methods listed for this paper. Add relevant methods here