Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations

Koorosh Aslansefat¹, Mojgan Hashemian¹, Martin Walker¹, Mohammed Naveed Akram², Ioannis Sorokos², Yiannis Papadopoulos¹,

¹University of Hull, ²Fraunhofer IESE

Paper arXiv Code

Nerfies turns selfie videos from your phone into free-viewpoint portraits.

Abstract

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models operate as black boxes, their inner workings opaque and mysterious, and it can be difficult to trust their conclusions without understanding how those conclusions are reached. Explainability is therefore a key aspect of improving trustworthiness: the ability to better understand, interpret, and anticipate the behaviour of ML models. To this end, we propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

Visual Effects

Using nerfies you can create fun visual effects. This Dolly zoom effect would be impossible without nerfies since it would require going through a wall.

Matting

As a byproduct of our method, we can also solve the matting problem by ignoring samples that fall outside of a bounding box during rendering.

Interpolating states

We can also animate the scene by interpolating the deformation latent codes of two input frames. Use the slider here to linearly interpolate between the left frame and the right frame.

Start Frame

End Frame

Re-rendering the input video

Using Nerfies, you can re-render a video from a novel viewpoint such as a stabilized camera by playing back the training deformations.

-->

BibTeX


      @article{aslansefat2023explaining,
  title={Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations},
  author={Aslansefat, Koorosh and Hashemian, Mojgan and Walker, Martin and Akram, Mohammed Naveed and Sorokos, Ioannis and Papadopoulos, Yiannis},
  journal={IEEE Software},
  year={2023},
  publisher={IEEE}
}