AI Paper Atlas

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

Parametric Majorization for Data-Driven Energy Minimization Methods

Jonas Geiping, Michael Moeller

ICCV 2019 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 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
add the iterative majorization scheme on top of the single Bregman-type surrogate for 3 3x3 filters (ablation)parametric majorization (analysis operator denoising) · BSDS denoising (3 3x3 filters)PSNR: 26.66 -> 27.66Improved
add the iterative majorization scheme for 48 7x7 filters (ablation)parametric majorization (analysis operator denoising) · BSDS denoising (48 7x7 filters)PSNR: 27.41 -> 28.03Improved
add the iterative majorization scheme for 96 9x9 filters (ablation)parametric majorization (analysis operator denoising) · BSDS denoising (96 9x9 filters)PSNR: 27.46 -> 28.03Improved
increase filter bank from 3 3x3 to 48 7x7 filters (single surrogate)parametric majorization (analysis operator denoising) · BSDS denoisingPSNR: 26.66 -> 27.41Improved
increase filters from 48 7x7 to 96 9x9 (single surrogate)parametric majorization (analysis operator denoising) · BSDS denoisingPSNR: 27.41 -> 27.46No clear effect
scale model from 48 7x7 to 96 9x9 filters in training timeparametric majorization (analysis operator denoising) · BSDS denoisingtraining time per surrogate: 02:45 -> 01:43Improved
learned model with surrogate instead of prior implicit-differentiation training for 96 9x9 filtersanalysis operator denoising · BSDS denoisingtraining time: 20 days -> 01:43Improved
add learned linear correction term trained with gradient-penalty surrogate to Huber-TV CT reconstructionHuber-regularized CT reconstruction · Shepp-Logan phantom CTPSNR: almost 2dBImproved
add perimeter (TV) term trained end-to-end with surrogate to linear segmentation modelvariational segmentation, linear model · Cityscapes subset (4 images)training accuracyImproved
add a small number of iterations of the iterative scheme (four) to the surrogate for segmentation (ablation)variational segmentation, linear model · Cityscapes subset (4 images)training accuracyImproved

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