# Posthoc Interpretation via Quantization

arXiv: https://arxiv.org/abs/2303.12659 · HTML: https://mlsanity.com/paper/2303.12659/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images](https://mlsanity.com/paper/1512.02017/) (2015)
- [Explaining a black-box using Deep Variational Information Bottleneck Approach](https://mlsanity.com/paper/1902.06918/) (2019)
- [MultiViz: Towards Visualizing and Understanding Multimodal Models](https://mlsanity.com/paper/2207.00056/) (2022)
- [A Framework to Learn with Interpretation](https://mlsanity.com/paper/2010.09345/) (2020)
- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)

## Built on by (most cited first, 7 of 7)

- [Open-Source Conversational AI with SpeechBrain 1.0](https://mlsanity.com/paper/2407.00463/) (2024)
- [Focal Modulation Networks for Interpretable Sound Classification](https://mlsanity.com/paper/2402.02754/) (2024)
- [LMAC-TD: Producing Time Domain Explanations for Audio Classifiers](https://mlsanity.com/paper/2409.08655/) (2024)
- [Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech](https://mlsanity.com/paper/2411.08013/) (2024)
- [What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain](https://mlsanity.com/paper/2501.13887/) (2025)
- [Listenable Maps for Zero-Shot Audio Classifiers](https://mlsanity.com/paper/2405.17615/) (2024)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)

## Abstract (arXiv)

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.