AI Paper Atlas

Research map / Image generation / Image restoration

Supplementary Meta-Learning: Towards a Dynamic Model for Deep Neural Networks

Feihu Zhang, Benjamin W. Wah

ICCV 2017 · Image generation › Image restoration · approach: Priors for restoration networks · 4 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 dynamic MLNN layers to the CNNArc 1 super-resolution · Super-resolution Dataset-5PSNR (dB): 32.64 -> 32.87Improved
add MLNN to Arc 1 on less diverse dataArc 1 super-resolution · Super-resolution Dataset-1PSNR (dB): 29.97 -> 30.11Improved
add MLNN to 21-layer residual netArc 4 super-resolution · Super-resolution Dataset-5PSNR (dB): 32.99 -> 33.11Improved
add MLNN to denoising networksArc 1 denoising · Denoising BSDPSNR (dB): 28.71 -> 28.87Improved
add dynamic dot-product and addition rather than concatenation of the same branches (ablation)MLNN Arc 1 · Super-resolution Dataset-5PSNR (dB): 32.71 -> 32.87Improved
add dynamic Fw branch instead of fixed weights (ablation)MLNN Arc 1 · Super-resolution upsamplingPSNR (dB): 32.68 -> 32.87Improved
add learned Fb instead of identity mapping (ablation)MLNN Arc 1 · Super-resolution upsamplingPSNR (dB): 32.7 -> 32.87Improved
add dynamic Fw branch instead of fixed weights (ablation)MLNN AlexNet · ImageNettop-1 error: top-1 error rate increases by 0.61%Improved
add learned Fb instead of identity mapping (ablation)MLNN AlexNet · ImageNettop-1 error: top-1 error rate increases by 0.73%Improved
add MLNN to more AlexNet layers (MLNN-1 to MLNN-3) (ablation)AlexNet · ImageNettop-1 error (%): 42.2 -> 41.1Improved
convert further layers to MLNN (MLNN-5) (ablation)AlexNet · ImageNetaccuracy: accuracy begins to drop by 0.2%Hurt
add MLNN to MNIST fully-connected layerArc 5 · MNISTerror rate (%): 1.11 -> 0.71Improved

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