Sergio Izquierdo, Javier Civera

Code and models for Optimal Transport Aggregation for Visual Place Recognition (DINOv2 SALAD).

We introduce DINOv2 SALAD, a Visual Place Recognition model that achieves state-of-the-art results on common benchmarks. We introduce two main contributions:

• Using a finetuned DINOv2 encoder to get richer and more powerful features.
• A new aggregation technique based on optimal transport to create a global descriptor based on optimal transport. This aggregation extends NetVLAD to consider feature-to-cluster relations as well as cluster-to-features. Besides, it includes a dustbin to discard uninformative features.

For more details, check the paper at arXiv.

It has been tested on Pytorch 2.1.0 with CUDA 12.1 and Xformers. Create a ready to run environment with:

conda env create -f environment.yml

To quickly test and use our model, you can use Torch Hub:

import torch
model = torch.hub.load("serizba/salad", "dinov2_salad")
model.eval()
model.cuda()

For training, download GSV-Cities dataset. For evaluation download the desired datasets (MSLS, NordLand, SPED, or Pittsburgh)

Training is done on GSV-Cities for 4 complete epochs. It requires around 30 minutes on an NVIDIA RTX 3090. For training DINOv2 SALAD run:

python3 main.py

After training, logs and checkpoints should be on the logs dir.

You can download a pretrained DINOv2 SALAD model from here. For evaluating run:

python3 eval.py --ckpt_path 'weights/dino_salad.ckpt' --image_size 322 322 --batch_size 256 --val_datasets MSLS Norrdland

This code is based on the amazing work of:

• MixVPR
• GSV-Cities
• DINOv2