# Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation

arXiv: https://arxiv.org/abs/2002.09103 · HTML: https://mlsanity.com/paper/2002.09103/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2020.

## Built on by (most cited first, 30 of 61)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models](https://mlsanity.com/paper/2307.10236/) (2023)
- [Nonparametric Uncertainty Quantification for Single Deterministic Neural Network](https://mlsanity.com/paper/2202.03101/) (2022)
- [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)
- [TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation](https://mlsanity.com/paper/2303.09870/) (2023)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [Understanding Test-Time Augmentation](https://mlsanity.com/paper/2402.06892/) (2024)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [MVDG: A Unified Multi-view Framework for Domain Generalization](https://mlsanity.com/paper/2112.12329/) (2021)
- [Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification](https://mlsanity.com/paper/2409.00755/) (2024)
- [Exploring Train and Test-Time Augmentations for Audio-Language Learning](https://mlsanity.com/paper/2210.17143/) (2022)
- [Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding](https://mlsanity.com/paper/2403.17010/) (2024)
- [A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning](https://mlsanity.com/paper/2406.00332/) (2024)
- [Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection](https://mlsanity.com/paper/2408.00619/) (2024)
- [An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2201.11440/) (2022)
- [Using Artificial Populations to Study Psychological Phenomena in Neural Models](https://mlsanity.com/paper/2308.08032/) (2023)
- [Improving Black-box Robustness with In-Context Rewriting](https://mlsanity.com/paper/2402.08225/) (2024)
- [DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models](https://mlsanity.com/paper/2302.10341/) (2023)
- [Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks](https://mlsanity.com/paper/2304.05104/) (2023)
- [U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences](https://mlsanity.com/paper/2512.02982/) (2025)
- [Mean Embeddings with Test-Time Data Augmentation for Ensembling of Representations](https://mlsanity.com/paper/2106.08038/) (2021)
- [Evidential Deep Partial Multi-View Classification With Discount Fusion](https://mlsanity.com/paper/2408.13123/) (2024)
- [Compensation Learning in Semantic Segmentation](https://mlsanity.com/paper/2304.13428/) (2023)
- [Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models](https://mlsanity.com/paper/2306.08909/) (2023)
- [From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?](https://mlsanity.com/paper/2310.05341/) (2023)

## Abstract (arXiv)

Test-time data augmentation-averaging the predictions of a machine learning model across multiple augmented samples of data-is a widely used technique that improves the predictive performance. While many advanced learnable data augmentation techniques have emerged in recent years, they are focused on the training phase. Such techniques are not necessarily optimal for test-time augmentation and can be outperformed by a policy consisting of simple crops and flips. The primary goal of this paper is to demonstrate that test-time augmentation policies can be successfully learned too. We introduce greedy policy search (GPS), a simple but high-performing method for learning a policy of test-time augmentation. We demonstrate that augmentation policies learned with GPS achieve superior predictive performance on image classification problems, provide better in-domain uncertainty estimation, and improve the robustness to domain shift.