Suppressing Non-Semantic Noise in Masked Image Modeling Representations

Martine Hjelkrem-Tan, Marius Aasan, Rwiddhi Chakraborty, Gabriel Y. Arteaga, Changkyu Choi, Adín Ramírez Rivera

DSB @ IFI @ UiO

This repo contains code and weights for Suppressing Non-Semantic Noise in Masked Image Modeling Representations, accepted for CVPR 2026.

For an introduction to our work, visit the project webpage.

Installation

The package can be installed via:

# HTTPS
pip install git+https://github.com/dsb-ifi/soap.git

# SSH
pip install git+ssh://git@github.com/dsb-ifi/soap.git

Measuring Semantic Invariance and Using SOAP

We provide a Jupyter notebook that illustrates how to get started with calculating the SI score and SOAP, and gives an example usecase for salient segmentation.

Citation

If you find our work useful, please consider citing our paper.

@inproceedings{hjelkremtan2025soap,
  title={Suppressing Non-Semantic Noise in Masked Image Modeling Representations},
  author={Hjelkrem-Tan, Martine and Aasan, Marius and Chakraborty, Rwiddhi and Arteaga, Gabriel Y. and Choi, Changkyu and Ram\'irez Rivera, Ad\'in},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2026}
}