AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning

Xingping Dong, Jianbing Shen, Wenguan Wang, Yu Liu, Ling Shao, Fatih Porikli

CVPR 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 174 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Optimize Siam-py hyperparameters dynamically for each frameSiam-py · OTB-2013 OPEAUC: 0.597 to 0.629Improved
Optimize Siam-py hyperparameters dynamicallySiam-py · VOT-2015accuracy: 0.540 -> 0.578Improved
Optimize Siam-py hyperparameters dynamicallySiam-py · VOT-2015robustness: 1.366 -> 1.578Hurt
Optimize Siam-py hyperparameters dynamicallySiam-py · OTB-2013FPS: 74 FPS to 69 FPSHurt
Pre-train the action-predict network with supervised learning on original hyperparameters (ablation)NAF for tracking hyperparameter optimization · OTB-2013mean IoUImproved
Add the staged heuristic: pre-train the action network, learn value and matrix networks with the action network fixed, then train all networks (ablation)NAF for tracking hyperparameter optimization · OTB-2013mean IoUImproved
Use the original NAF training without the supervised action-network initialization (ablation)NAF for tracking hyperparameter optimization · OTB-2013mean IoUHurt
Use dynamic hyperparameter optimizationSiam-py · OTB-100precision: 1.5%Improved
Use dynamic hyperparameter optimizationSiam-py · OTB-100AUC: 3.3%Improved
Use dynamic hyperparameter optimizationSiam-py · OTB-50AUC: 7.4%Improved
Use dynamic hyperparameter optimizationSiam-py · OTB-100 attributes: SV, OCC, MB, FM, IPR, OPRoverlap successImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy