Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912254346133504 |
|---|---|
| author | Hausler, Stephen Moghadam, Peyman |
| author_facet | Hausler, Stephen Moghadam, Peyman |
| contents | In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modelling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modelling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders. The Pair-VPR website is: https://csiro-robotics.github.io/Pair-VPR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06614 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers Hausler, Stephen Moghadam, Peyman Robotics Artificial Intelligence Computer Vision and Pattern Recognition In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modelling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modelling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders. The Pair-VPR website is: https://csiro-robotics.github.io/Pair-VPR. |
| title | Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.06614 |