AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Lifting Layers: Analysis and Applications

Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller

ECCV 2018 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 8 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
replace ReLU with lifting activationone-hidden-layer FC network · MNISTbest test error (%): 3.07% -> 2.61%Improved
replace maxout with lifting activation at similar parameter countone-hidden-layer FC network · MNISTbest test error (%): 2.91% -> 2.61%Improved
replace ReLU with lifting layers (L=3) in ME-model+BNME-model+BN · CIFAR-10 and CIFAR-100test errorImproved
add lifting layers instead of enlarging the ReLU model (Large ME-model+BN, more parameters) (ablation)ME-model+BN · CIFAR-10 and CIFAR-100test errorImproved
add batch normalization to ME-model (ablation)ME-model · CIFAR-10 and CIFAR-100test errorImproved
increase model size (Large ME-model+BN) (ablation)ME-model+BN · CIFAR-10 and CIFAR-100test errorImproved
replace ReLU with lifting layers (L=3) in a DnCNN-style denoiser (Lift-46)DnCNN-S · BSD68 sigma=15PSNR (dB): 31.72 -> 31.72No clear effect
replace ReLU with lifting layers (L=3) in a DnCNN-style denoiser (Lift-46)DnCNN-S · BSD68 sigma=25PSNR (dB): 29.21 -> 29.21No clear effect
replace ReLU with lifting layers (L=3) in a DnCNN-style denoiser (Lift-46)DnCNN-S · BSD68 sigma=50PSNR (dB): 26.21 -> 26.23Improved
replace parameterized filtering with lifting of the input for dimensionality increaseStd-Net · 2-D function fitting cos(x2 sin(x1))convergence and approximation RMSEImproved
replace ReLU network with lifting-based linear model on 1-D sine fittingStd-Net · 1-D sine fitting (50 training examples)convergenceImproved
lift a truncated linear loss into a convex problemregression with 40% outliers · synthetic robust regressionfit qualityImproved

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