pecl

Paired embeddings contrastive learning

https://github.com/vdplasthijs/pecl

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org, zenodo.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (13.1%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

Paired embeddings contrastive learning

Basic Info

Host: GitHub
Owner: vdplasthijs
License: mit
Language: Jupyter Notebook
Default Branch: main
Homepage: https://arxiv.org/abs/2505.09306
Size: 84.1 MB

Statistics

Stars: 1
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created about 2 years ago · Last pushed 9 months ago

Metadata Files

Readme License Citation

Predicting butterfly species presence from satellite imagery using soft contrastive regularisation

This repository contains all code of our 2025 CVPR FGVC paper, including: - PECL (Paired Embeddings Contrastive Loss) implementation in scripts/paired_embeddings_models.py. - Torch dataloader for the S2BMS dataset in scripts/DataSetImagePresence.py - Resnet-based model to predict species presence vectors from satellite images, using PECL.

Installation:

Use conda to install packages using pecl.yml or pip install from requirements.txt.
Add your user profile data paths in content/data_paths_pecl.json. (This step is not needed when just experimenting with the code and the example data provided in the repo).

Getting started:

A sample data set (of 16 locations) is provided in tests/data_tests/.
Go to notebooks/Getting started.ipynb to see examples of how to load the data and model.

Data:

The full S2-BMS data set is available on Zenodo.
Our Torch dataloader is available in scripts/DataSetImagePresence.py.

PECL implementation

For details please see our paper.
PyTorch implementation can be found in scripts/paired_embeddings_models.py (ImageEncoder.pecl_loss()).

Results

The training scripts used for the paper are scripts/train.py and scripts/train_randomsearch.py.
The figures and tables in the paper were created in notebooks/Results figs and tables.ipynb.

Please cite our paper if you use this method or data in a publication - thank you!!

Owner

Name: Thijs van der Plas
Login: vdplasthijs
Kind: user
Location: Oxford, UK
Company: The Alan Turing Institute

Website: https://www.turing.ac.uk/people/research-associates/dr-thijs-van-der-plas
Twitter: vdplasthijs
Repositories: 22
Profile: https://github.com/vdplasthijs

Post doctoral researcher @ The Alan Turing Institute

Citation (CITATION.bib)

@article{van2025predicting,
  title={Predicting butterfly species presence from satellite imagery using soft contrastive regularisation},
  author={van der Plas, Thijs L and Law, Stephen and Pocock, Michael JO},
  journal={arXiv preprint arXiv:2505.09306},
  year={2025},
  url={https://arxiv.org/abs/2505.09306}
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science