# Classification Confidence Estimation with Test-Time Data-Augmentation

arXiv: https://arxiv.org/abs/2006.16705 · HTML: https://mlsanity.com/paper/2006.16705/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning](https://mlsanity.com/paper/2505.13115/) (2025)
- [Steerable Equivariant Representation Learning](https://mlsanity.com/paper/2302.11349/) (2023)
- [BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging](https://mlsanity.com/paper/2406.17640/) (2024)
- [FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs](https://mlsanity.com/paper/2509.16648/) (2025)
- [Rethinking and Recomputing the Value of Machine Learning Models](https://mlsanity.com/paper/2209.15157/) (2022)
- [Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time](https://mlsanity.com/paper/2410.01083/) (2024)
- [Confidence Calibration with Bounded Error Using Transformations](https://mlsanity.com/paper/2102.12680/) (2021)
- [Quantifying and Improving Adaptivity in Conformal Prediction through Input Transformations](https://mlsanity.com/paper/2511.11472/) (2025)
- [Confidence-Aware Automated Assessment of Student-Drawn Scientific Models](https://mlsanity.com/paper/2606.20264/) (2026)
- [What Paired Evaluations Reveal under Visual Perturbations](https://mlsanity.com/paper/2609.35583/) (2026)

## Abstract (arXiv)

Machine learning plays an increasingly significant role in many aspects of our lives (including medicine, transportation, security, justice and other domains), making the potential consequences of false predictions increasingly devastating. These consequences may be mitigated if we can automatically flag such false predictions and potentially assign them to alternative, more reliable mechanisms, that are possibly more costly and involve human attention. This suggests the task of detecting errors, which we tackle in this paper for the case of visual classification. To this end, we propose a novel approach for classification confidence estimation. We apply a set of semantics-preserving image transformations to the input image, and show how the resulting image sets can be used to estimate confidence in the classifier's prediction. We demonstrate the potential of our approach by extensively evaluating it on a wide variety of classifier architectures and datasets, including ResNext/ImageNet, achieving state of the art performance. This paper constitutes a significant revision of our earlier work in this direction (Bahat & Shakhnarovich, 2018).