# Class Introspection: A Novel Technique for Detecting Unlabeled Subclasses by Leveraging Classifier Explainability Methods

arXiv: https://arxiv.org/abs/2107.01657 · HTML: https://mlsanity.com/paper/2107.01657/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 4 Jul 2021.

## Builds on (most cited first, 8 of 8)

- [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)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience](https://mlsanity.com/paper/2001.09219/) (2020)
- ["Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users](https://mlsanity.com/paper/1805.08578/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Review of Pseudo-Labeling for Computer Vision](https://mlsanity.com/paper/2408.07221/) (2024)

## Abstract (arXiv)

Detecting latent structure within a dataset is a crucial step in performing analysis of a dataset. However, existing state-of-the-art techniques for subclass discovery are limited: either they are limited to detecting very small numbers of outliers or they lack the statistical power to deal with complex data such as image or audio. This paper proposes a solution to this subclass discovery problem: by leveraging instance explanation methods, an existing classifier can be extended to detect latent classes via differences in the classifier's internal decisions about each instance. This works not only with simple classification techniques but also with deep neural networks, allowing for a powerful and flexible approach to detecting latent structure within datasets. Effectively, this represents a projection of the dataset into the classifier's "explanation space," and preliminary results show that this technique outperforms the baseline for the detection of latent classes even with limited processing. This paper also contains a pipeline for analyzing classifiers automatically, and a web application for interactively exploring the results from this technique.