Learning Super-Features for Image Retrieval

Fork from https://github.com/naver/FIRe, removing dependences of several submodules via adding these moudules to lib with path setting.

This repo is integrated to Hierarchical-Localization pipline by adding hloc/extractors/fire.py interface.

This repository contains the code for running FIRe model presented in our ICLR'22 paper:

@inproceedings{superfeatures,
  title={{Learning Super-Features for Image Retrieval}},
  author={{Weinzaepfel, Philippe and Lucas, Thomas and Larlus, Diane and Kalantidis, Yannis}},
  booktitle={{ICLR}},
  year={2022}
}

License

The code is distributed under the CC BY-NC-SA 4.0 License. See LICENSE for more information. It is based on code from HOW, cirtorch and ASMK that are released under their own license, the MIT license.

Preparation

1. install ASMK

pip3 install pyaml numpy faiss-gpu 
cd lib/asmk
python3 setup.py build_ext --inplace
rm -r build

2. install dependencies by running:

pip3 install -r requirements.txt

3. data/experiments folders

All data will be stored under a folder fire_data that will be created when running the code; similarly, results and models from all experiments will be stored under folder fire_experiments

Evaluating our ICLR'22 FIRe model

To evaluate on ROxford/RParis our model trained on SfM-120k, simply run

python evaluate.py eval_fire.yml

With the released model and the parameters found in eval_fire.yml, we obtain 90.3 on the validation set, 82.6 and 62.2 on ROxford medium and hard respectively, 85.2 and 70.0 on RParis medium and hard respectively.

Training a FIRe model

Simply run

python train.py train_fire.yml -e train_fire

All training outputs will be saved to fire_experiments/train_fire.

To evaluate the trained model that was saved in fire_experiments/train_fire, simply run:

python evaluate.py eval_fire.yml -e train_fire -ml train_fire

Pretrained models

For reproducibility, we provide the following model weights for the architecture we use in the paper (ResNet50 without the last block + LIT):

• Model pre-trained on ImageNet-1K (with Cross-Entropy, the pre-trained model we use for training FIRe) (link) or fire_imagenet.pth
• Model trained on SfM-120k trained with FIRe (link) or fire_SfM_120k.pth

They will be automatically downloaded when running the training / testing script.