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

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

21 Feb 2020arXiv:2002.09103archive 2025-07-28

Dmitry Molchanov, Alexander Lyzhov, Yuliya Molchanova, Arsenii Ashukha, Dmitry Vetrov

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: GPS

GPS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections