Image Data Augmentation

Greedy Policy Search

Introduced by Molchanov et al. in Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation

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.

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

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Autonomous Driving 19 6.91%
Time Series 15 5.45%
Management 10 3.64%
Semantic Segmentation 10 3.64%
BIG-bench Machine Learning 10 3.64%
Object Detection 8 2.91%
Anomaly Detection 7 2.55%
Indoor Localization 6 2.18%
Decision Making 6 2.18%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories