soft-brownian-offset

Soft Brownian Offset (SBO) defines an iterative approach to translate points by a most likely distance from a given dataset. It can be used for generating out-of-distribution samples.

Installation

This project is hosted on PyPI and can therefore be installed easily through pip:

pip install sbo

Dependending on your setup you may need to add --user after the install.

Usage

For brevity's sake here's a short introduction to the library's usage:

from sklearn.datasets import make_moons
from sbo import soft_brownian_offset

X, _ = make_moons(n_samples=60, noise=.08)
X_ood = soft_brownian_offset(X, d_min=.35, d_off=.24, n_samples=120, softness=0)

For more details please see the documentation.

Background

The technique allows for trivial OOD generation -- as shown above -- or more complex schemes that apply the transformation of learned representations. For an in-depth look at the latter please refer to the paper that is also available as a pre-print on arXiv. For citations please see cite.

Demonstration

See the following plot to gain intuition on the approach's results:

Please see the documentation for the source code to recreate the plot.

Cite

Please cite SBO in your paper if it helps your research:

@inproceedings{MBH21,
  author    = {Möller, Felix and Botache, Diego and Huseljic, Denis and Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard},
  booktitle = {{Proc. of CVPR SAIAD Workshop}},
  title     = {{Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders}},
  year      = 2021
}