# Confidence from Invariance to Image Transformations

arXiv: https://arxiv.org/abs/1804.00657 · HTML: https://mlsanity.com/paper/1804.00657/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2018.

## Built on by (most cited first, 6 of 6)

- [Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?](https://mlsanity.com/paper/2105.09270/) (2021)
- [3D Reconstruction of Objects in Hands without Real World 3D Supervision](https://mlsanity.com/paper/2305.03036/) (2023)
- [WOOD: Wasserstein-based Out-of-Distribution Detection](https://mlsanity.com/paper/2112.06384/) (2021)
- [Learning Complementary Policies for Human-AI Teams](https://mlsanity.com/paper/2302.02944/) (2023)
- [Matrix Factorization for Inferring Associations and Missing Links](https://mlsanity.com/paper/2503.04680/) (2025)
- [Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning](https://mlsanity.com/paper/2610.08894/) (2026)

## Abstract (arXiv)

We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier. Our method is agnostic to the form of the classifier, requiring access only to classifier responses to a set of inputs. We train a parametric binary classifier (error/correct) on a representation derived from a set of classifier responses generated from multiple copies of the same input, each subject to a different natural image transformation. Thus, we establish a measure of confidence in classifier's decision by analyzing the invariance of its decision under various transformations. In experiments with multiple data sets (STL-10,CIFAR-100,ImageNet) and classifiers, we demonstrate new state of the art for the error detection task. In addition, we apply our technique to novelty detection scenarios, where we also demonstrate state of the art results.