AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Efficient Subpixel Refinement With Symbolic Linear Predictors

Vincent Lui, Jonathon Geeves, Winston Yii, Tom Drummond

CVPR 2018 · Learning theory and algorithms › Combinatorial and search optimization · approach: Predict-then-optimize learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
Use symbolic representations to learn the linear predictorLinear Predictors for synthetic subpixel refinement · Synthetic experiment, 9×9 patch, m=5000RMSEImproved
Use symbolic representations instead of conventional LP trainingLinear Predictors for subpixel refinement · Synthetic experimenttraining timeImproved
Use the symbolic predictor for refinementSubpixel refinement · Localization experimentATE (mm): 8.1 -> 2.3Improved
Select the best 250 keypoints by predicted error rather than using the worst 250Symbolic Linear Predictors · Localization experimentATE (mm): 3.1 -> 2.3Improved
Combine symbolic predictors with DCT-25 (ablation)Symbolic Linear Predictors · Hannover image pairsRMSEMixed
Retain fewer, low-frequency DCT coefficients (ablation)Linear Predictors · Hannover image pairsRMSEImproved
Increase the number of sample warps (ablation)Linear Predictors · Synthetic experimentRMSEImproved
Increase the patch size (ablation)Linear Predictors · Synthetic experimentRMSEImproved
Increase maximum parameter variation during training (ablation)Linear Predictors · Synthetic experimentRMSEHurt
Use symbolic learning instead of conventional learning for the same LP (ablation)Linear Predictors · Synthetic experimentRMSENo clear effect
Use DCT-25 with symbolic learning instead of DCT-25 alone (ablation)Linear Predictors · Synthetic experimentRMSENo clear effect

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