GPS

2000년 도입 · 논문 707편에서 사용

Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with an empty policy and builds it in an iterative fashion. Each step selects a sub-policy that provides the largest improvement in calibrated log-likelihood of ensemble predictions and adds it to the current policy.

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

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