AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior

Metin Ersin Arican, Ozgur Kara, Gustav Bredell, Ender Konukoglu

CVPR 2022 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 19 citations (OpenAlex)

Check 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
Select image-specific architectures using PSD DB Strip MSEDIP · BM3D denoising (σ=25)PSNR: 27.87 -> 28.39Improved
Select image-specific architectures using PSD DB Strip MSEDIP · Set12 denoising (σ=25)PSNR: 27.92 -> 28.06Improved
Select image-specific architectures using PSD DB Strip MSEDIP · CBM3D denoising (σ=25)PSNR: 28.93 -> 30.36Improved
Select image-specific architectures using PSD DB MSEDIP · BM3D inpaintingPSNR: 31.04 -> 32.90Improved
Select image-specific architectures using PSD DB MSEDIP · Set12 inpaintingPSNR: 31.00 -> 32.22Improved
Use image-specific PSD metrics for architecture selectionDIP · Super-resolution, Set5 ×2 and ×4; Set14 ×2, ×4, and ×8PSNRHurt
Restrict the PSD comparison to a frequency strip, avoiding the full PSD (ablation)ISNAS-DIP · DenoisingPSNR: 24.31 -> 28.39; 23.77 -> 28.06; 30.01 -> 30.36Improved
Use PSD DB Strip MSE rather than whole-PSD DB MSE (ablation)ISNAS-DIP · Super-resolutionPSNR: 34.83 -> 34.72; 30.22 -> 30.05; 23.97 -> 23.90Mixed
Use PSD DB Strip MSE rather than PSD DB MSE (ablation)ISNAS-DIP · BM3D inpaintingPSNR: 32.90 -> 32.32Hurt
Use resized averaging selection rather than full-sized averaging selection (ablation)PSD DB Strip MSE selection · DenoisingPSNR: 27.66 -> 28.39; 27.40 -> 28.06; 29.28 -> 30.36Hurt
Use resized averaging selection rather than full-sized averaging selection (ablation)PSD DB Strip MSE selection · InpaintingPSNR: 33.01 -> 32.32; 32.17 -> 31.68Mixed
Select candidates by PSD DB Strip MSE rather than random search-space selection (ablation)ISNAS-DIP · DenoisingPSNR: 23.20 -> 27.66; 22.66 -> 27.40; 27.86 -> 29.28Improved

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