AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Multiscale Adaptive Representation of Signals: I. The Basic Framework

Cheng Tai, Weinan E

JMLR 2016 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 16 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
learn AdaFrame filters from clean images instead of the noisy imageAdaFrame denoising · Single image denoising (sigma=0.1)PSNR (dB): 28.8 -> 29.3Improved
learn filters from clean images instead of noisy imagesAdaFrame · Extended Yale B (noisy, sigma=0.1)PSNR (dB): 31.35 -> 32.07Improved
learn filters from clean images instead of noisy imagesK-SVD · Extended Yale B (noisy, sigma=0.1)PSNR (dB): 31.4 -> 32.01Improved
replace K-SVD with AdaFrame (noisy-learned filters)denoising · Single image denoising (sigma=0.1)PSNR (dB): 28.65 -> 28.8Improved
increase AdaFrame filter support from 8x8 to 12x12 (ablation)AdaFrame denoising · Barbara sigma=0.05PSNR (dB): 31.87 -> 33.22Improved
increase AdaFrame filter support from 8x8 to 12x12 (ablation)AdaFrame denoising · House sigma=0.1PSNR (dB): 31.19 -> 31.45Improved
increase K-SVD patch size from 8x8 to 12x12 (ablation)K-SVD denoising · Boat sigma=0.1PSNR (dB): 29.19 -> 28.70Hurt
use AdaFrame 12x12 instead of K-SVD 12x12denoising · Lena sigma=0.1PSNR (dB): 30.84 -> 31.39Improved
use AdaFrame 8x8 instead of K-SVD 8x8denoising · House sigma=0.1PSNR (dB): 32.15 -> 31.19Hurt
use AdaFrame instead of K-SVD for speeddenoising runtime · Denoising runtime (laptop, 8x8 support)denoising time (s): 6.5s -> 0.6sImproved
use AdaFrame filters instead of K-SVD dictionary trainingtraining runtime · Denoising runtime (laptop, 8x8 support)training time (s): 25s -> 3.7sImproved
increase number of filters from 6 to 12 (ablation)AdaFrame features · MNISTprecision: 97.0 % -> 97.4%Improved

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