AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Training Binary Neural Network without Batch Normalization for Image Super-Resolution

Xinrui Jiang, Nannan Wang, Jingwei Xin, Keyu Li, Xi Yang, Xinbo Gao

AAAI 2021 · Architectures and efficiency › RNNs and normalization · approach: Batch normalization improvements · 39 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
Apply the full IBTM method instead of IRNet binarizationVDSR · Set5 ×2PSNR: 36.94 -> 37.24Improved
Apply the full IBTM method instead of IRNet binarizationVDSR · Set14 ×2PSNR: 32.64 -> 32.82Improved
Apply the full IBTM method instead of IRNet binarizationVDSR · B100 ×2PSNR: 31.47 -> 31.60Improved
Apply the full IBTM method instead of IRNet binarizationVDSR · Urban100 ×2PSNR: 29.80 -> 30.14Improved
Apply the full IBTM method instead of RTN binarizationEDSR · Set5 ×4PSNR: 31.49 -> 31.84Improved
Apply the full IBTM method instead of RTN binarizationEDSR · Set14 ×4PSNR: 28.14 -> 28.33Improved
Apply the full IBTM method instead of RTN binarizationEDSR · B100 ×4PSNR: 27.27 -> 27.42Improved
Apply the full IBTM method instead of RTN binarizationEDSR · Urban100 ×4PSNR: 25.20 -> 25.54Improved
Add a multiple receptive-field block (ablation)VDSR binary SR · Set5 ×2PSNR: 37.06 -> 37.16Improved
Add a multiple receptive-field block (ablation)VDSR binary SR · B100 ×2PSNR: 31.53 -> 31.57Improved
Add distribution-based distillation loss (ablation)VDSR + MRB · Set5 ×2PSNR: 37.16 -> 37.19Improved
Add distribution-based distillation loss (ablation)VDSR + MRB · B100 ×2PSNR: 31.57 -> 31.58Improved

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