Research map / Label-efficient and robust learning / Self-supervised and contrastive
SAH-SCI: Self-Supervised Adapter for Efficient Hyperspectral Snapshot Compressive Imaging
Haijin Zeng, Yuxi Liu, Yongyong Chen, Youfa Liu, Chong Peng, Jingyong Su
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 SAH self-supervised adapter to pre-trained reconstruction models | HDNet · ICVL | avg PSNR: 28.91 -> 34.78 | Improved |
| apply SAH adapter to all 7 pre-trained models | end-to-end and unfolding models · ICVL | avg PSNR: over 2dB average PSNR improvement | Improved |
| apply SAH to DAUHST on NTIRE2022 | DAUHST · NTIRE2022 | PSNR: 38.44 -> 38.71 | No clear effect |
| add frequency adaption module to SAH (ablation) | SAH on λ-Net · ICVL | PSNR: 29.21 -> 29.95 | Improved |
| use 3-layer instead of 2-layer SAH (ablation) | SAH on λ-Net · ICVL | PSNR: 29.95 -> 30.15 | No clear effect |
| replace normal convolution with spatial-spectral convolution (ablation) | SAH on λ-Net · ICVL | PSNR: 29.95 -> 29.45 PSNR, params 2.09M -> 0.26M | Mixed |
| add channel weighting to SSConv (ablation) | SAH on λ-Net · ICVL | PSNR: 29.45 -> 29.98 | Improved |
| add equivariance imaging loss (ablation) | SAH-SCI on HDNet · ICVL | PSNR: 33.35 -> 34.31 | Improved |
| add image uncertainty loss (ablation) | SAH-SCI on HDNet · ICVL | PSNR: 33.35 -> 33.79 | Improved |
| add total variation loss (ablation) | SAH-SCI on HDNet · ICVL | PSNR: 34.50 -> 34.78 | Improved |
| full fine-tuning of pre-trained model instead of adapter | HDNet · ICVL/Harvard/NTIRE | PSNR/SSIM | Hurt |
Closest papers by meaning
- End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention (ECCV 2020 · similarity 0.91)
- Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging (CVPR 2021 · similarity 0.91)
- Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction (ECCV 2022 · similarity 0.90)
- Self-Supervised Neural Networks for Spectral Snapshot Compressive Imaging (ICCV 2021 · similarity 0.90)
- Dual-Window Multiscale Transformer for Hyperspectral Snapshot Compressive Imaging (AAAI 2024 · similarity 0.89)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.88)
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.
