AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-Supervised Neural Networks for Spectral Snapshot Compressive Imaging

Ziyi Meng, Zhenming Yu, Kun Xu, Xin Yuan

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 144 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 plug-and-play framework around DIP instead of sole DIP (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 26.99 -> 30.48Improved
use double fidelity terms instead of single fidelity term (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 28.87 -> 30.48Improved
use DIP U-net prior instead of deep decoder (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 28.44 -> 30.48Improved
use ConvTranspose upsampling instead of bilinear (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 29.69 -> 30.48Improved
use ConvTranspose upsampling instead of PixelShuffle (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 27.59 -> 30.48Improved
use average-pooling instead of max-pooling (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 30.26 -> 30.48Improved
add pre-trained HSI deep denoiser to PnP-DIP (ablation)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 30.48 -> 31.30Improved
compare untrained PnP-DIP with supervised TSA-NetPnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 30.15 -> 30.48Improved
compare untrained PnP-DIP with supervised TSA-Net on SSIMPnP-DIP · CASSI synthetic, 10 scenes avgSSIM: 0.893 -> 0.854Hurt
add Poisson noise SNR=25dB to measurements (supervised TSA-Net)TSA-Net · CASSI synthetic, 10 scenes avgPSNR (dB): 30.15 -> 24.15Hurt
add Poisson noise SNR=25dB to measurements (PnP-DIP)PnP-DIP · CASSI synthetic, 10 scenes avgPSNR (dB): 30.48 -> 27.73Hurt
use a larger 60-pixel real-mask shift instead of 30-pixel binary mask: PnP-DIP vs PnP-HSI gapPnP-DIP · ICVLPSNR (dB): 32.91 -> 37.27Improved

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