Methods › Computer Vision › Image Data Augmentation › GPS
Greedy Policy Search
GPS
Introduced by Dmitry Molchanov et al. in Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
30 shown of 707, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Geo-Registration of Terrestrial LiDAR Point Clouds with Satellite Images without GNSS 8 Jul 2025 · 0 repositories · arXiv:2507.05999
-
Curriculum-Guided Antifragile Reinforcement Learning for Secure UAV Deconfliction under Observation-Space Attacks 26 Jun 2025 · 0 repositories · arXiv:2506.21129
-
USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways 23 Jun 2025 · 0 repositories · arXiv:2506.18737
-
Quantum Artificial Intelligence for Secure Autonomous Vehicle Navigation: An Architectural Proposal 19 Jun 2025 · 0 repositories · arXiv:2506.16000
-
TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis 19 Jun 2025 · 1 repository · arXiv:2506.16401
-
Enhancing eLoran Timing Accuracy via Machine Learning with Meteorological and Terrain Data 18 Jun 2025 · 0 repositories · arXiv:2506.15235
-
M2BeamLLM: Multimodal Sensing-empowered mmWave Beam Prediction with Large Language Models 17 Jun 2025 · 0 repositories · arXiv:2506.14532
-
Towards Perception-based Collision Avoidance for UAVs when Guiding the Visually Impaired 17 Jun 2025 · 0 repositories · arXiv:2506.14857
-
A causal evaluation of Bogota's cable car illustrates the transformative potential of mobile phone data for policy analysis 11 Jun 2025 · 0 repositories · arXiv:2506.09311
-
Valuing Diffuse Global Public Goods from Satellite Constellations: Evidence from GPS and Airline Delays 9 Jun 2025 · 0 repositories · arXiv:2506.08209
-
End-to-End Framework for Robot Lawnmower Coverage Path Planning using Cellular Decomposition 6 Jun 2025 · 0 repositories · arXiv:2506.06028
-
Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system 6 Jun 2025 · 0 repositories · arXiv:2506.05999
-
The NetMob25 Dataset: A High-resolution Multi-layered View of Individual Mobility in Greater Paris Region 6 Jun 2025 · 0 repositories · arXiv:2506.05903
-
Vision-Based Autonomous MM-Wave Reflector Using ArUco-Driven Angle-of-Arrival Estimation 5 Jun 2025 · 0 repositories · arXiv:2506.05195
-
Towards Geometry Problem Solving in the Large Model Era: A Survey 3 Jun 2025 · 0 repositories · arXiv:2506.02690
-
Performance of leading large language models in May 2025 in Membership of the Royal College of General Practitioners-style examination questions: a cross-sectional analysis 3 Jun 2025 · 0 repositories · arXiv:2506.02987
-
A Provable Approach for End-to-End Safe Reinforcement Learning 28 May 2025 · 0 repositories · arXiv:2505.21852
-
STACI: Spatio-Temporal Aleatoric Conformal Inference 27 May 2025 · 0 repositories · arXiv:2505.21658
-
GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication 23 May 2025 · 1 repository · arXiv:2505.17530
-
PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints 23 May 2025 · 0 repositories · arXiv:2505.17445
-
Improving the Predictability of the Madden-Julian Oscillation at Subseasonal Scales with Gaussian Process Models 21 May 2025 · 0 repositories · arXiv:2505.15934
-
Modular Jump Gaussian Processes 21 May 2025 · 1 repository · arXiv:2505.15557
-
Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer 20 May 2025 · 2 repositories · arXiv:2505.13857
-
GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization 19 May 2025 · 0 repositories · arXiv:2505.13731
-
TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability 19 May 2025 · 0 repositories · arXiv:2505.12672
-
Geography-Aware Large Language Models for Next POI Recommendation 18 May 2025 · 0 repositories · arXiv:2505.13526
-
MMS-VPR: Multimodal Street-Level Visual Place Recognition Dataset and Benchmark 18 May 2025 · 0 repositories · arXiv:2505.12254
-
Graph and Simplicial Complex Prediction Gaussian Process via the Hodgelet Representations 16 May 2025 · 0 repositories · arXiv:2505.10877
-
Bidirectional Information Flow (BIF) -- A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization 16 May 2025 · 0 repositories · arXiv:2505.11294
-
STRIDE: Sparse Techniques for Regression in Deep Gaussian Processes 16 May 2025 · 0 repositories · arXiv:2505.11355
Tasks archive 2025-07-28
20 shown of 325 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Gaussian Processes | 153 |
| regression | 32 |
| Autonomous Driving | 30 |
| Uncertainty Quantification | 24 |
| Autonomous Vehicles | 20 |
| Bayesian Optimization | 20 |
| Management | 20 |
| Position | 20 |
| Time Series | 19 |
| Object Detection | 18 |
| Variational Inference | 18 |
| object-detection | 18 |
| Prediction | 17 |
| Decision Making | 16 |
| Representation Learning | 15 |
| Time Series Analysis | 15 |
| Retrieval | 14 |
| geo-localization | 14 |
| Deep Learning | 13 |
| Pose Estimation | 13 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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