English

Posthoc Interpretation via Quantization

Artificial Intelligence 2023-05-30 v2 Machine Learning Sound Audio and Speech Processing

Abstract

In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained classifiers. Our method utilizes vector quantization to transform the representations of a classifier into a discrete, class-specific latent space. The class-specific codebooks act as a bottleneck that forces the interpreter to focus on the parts of the input data deemed relevant by the classifier for making a prediction. Our model formulation also enables learning concepts by incorporating the supervision of pretrained annotation models such as state-of-the-art image segmentation models. We evaluated our method through quantitative and qualitative studies involving black-and-white images, color images, and audio. As a result of these studies we found that PIQ generates interpretations that are more easily understood by participants to our user studies when compared to several other interpretation methods in the literature.

Cite

@article{arxiv.2303.12659,
  title  = {Posthoc Interpretation via Quantization},
  author = {Francesco Paissan and Cem Subakan and Mirco Ravanelli},
  journal= {arXiv preprint arXiv:2303.12659},
  year   = {2023}
}

Comments

Francesco Paissan and Cem Subakan contributed equally

R2 v1 2026-06-28T09:28:19.651Z