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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Apply the full IBTM method instead of IRNet binarization | VDSR · Set5 ×2 | PSNR: 36.94 -> 37.24 | Improved |
| Apply the full IBTM method instead of IRNet binarization | VDSR · Set14 ×2 | PSNR: 32.64 -> 32.82 | Improved |
| Apply the full IBTM method instead of IRNet binarization | VDSR · B100 ×2 | PSNR: 31.47 -> 31.60 | Improved |
| Apply the full IBTM method instead of IRNet binarization | VDSR · Urban100 ×2 | PSNR: 29.80 -> 30.14 | Improved |
| Apply the full IBTM method instead of RTN binarization | EDSR · Set5 ×4 | PSNR: 31.49 -> 31.84 | Improved |
| Apply the full IBTM method instead of RTN binarization | EDSR · Set14 ×4 | PSNR: 28.14 -> 28.33 | Improved |
| Apply the full IBTM method instead of RTN binarization | EDSR · B100 ×4 | PSNR: 27.27 -> 27.42 | Improved |
| Apply the full IBTM method instead of RTN binarization | EDSR · Urban100 ×4 | PSNR: 25.20 -> 25.54 | Improved |
| Add a multiple receptive-field block (ablation) | VDSR binary SR · Set5 ×2 | PSNR: 37.06 -> 37.16 | Improved |
| Add a multiple receptive-field block (ablation) | VDSR binary SR · B100 ×2 | PSNR: 31.53 -> 31.57 | Improved |
| Add distribution-based distillation loss (ablation) | VDSR + MRB · Set5 ×2 | PSNR: 37.16 -> 37.19 | Improved |
| Add distribution-based distillation loss (ablation) | VDSR + MRB · B100 ×2 | PSNR: 31.57 -> 31.58 | Improved |
Closest papers by meaning
- Binarized Neural Network for Single Image Super Resolution (ECCV 2020 · similarity 0.92)
- Flexible Residual Binarization for Image Super-Resolution (ICML 2024 · similarity 0.89)
- Advanced Binary Neural Network for Single Image Super Resolution (IJCV 2023 · similarity 0.89)
- Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016 · similarity 0.87)
- SA-BNN: State-Aware Binary Neural Network (AAAI 2021 · similarity 0.87)
- Sub-Bit Neural Networks: Learning To Compress and Accelerate Binary Neural Networks (ICCV 2021 · similarity 0.87)
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.
