Research map / Learning theory and algorithms / Matrix and tensor methods
Convolutional Dictionary Learning via Local Processing
Vardan Papyan, Yaniv Romano, Jeremias Sulam, Michael Elad
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 |
|---|---|---|---|
| use slice-based dictionary learning instead of the Fourier-domain CSC method | convolutional dictionary learning · Image inpainting, test image 1 | PSNR (dB): 11.00 -> 11.67 | Improved |
| use slice-based dictionary learning instead of the Fourier-domain CSC method | convolutional dictionary learning · Image inpainting, test image 5 | PSNR (dB): 9.41 -> 9.18 | Hurt |
| train the dictionary on the corrupted image itself instead of the Fruit dataset | slice-based dictionary learning · Image inpainting, test image 1 | PSNR (dB): 11.67 -> 15.20 | Improved |
| train the dictionary on the corrupted image itself instead of the Fruit dataset | slice-based dictionary learning · Image inpainting, test image 5 | PSNR (dB): 9.18 -> 11.45 | Improved |
| train the dictionary on the corrupted image itself instead of the Fruit dataset | slice-based dictionary learning · Image inpainting, test image 2 | PSNR (dB): 10.33 -> 11.60 | Improved |
| use slice-based dictionary learning instead of the Fourier-domain CSC method | convolutional dictionary learning · Image inpainting, cropped region visual comparison | PSNR (dB): 5.22 -> 6.24 | Improved |
| train the dictionary on the corrupted image itself instead of the Fruit dataset | slice-based dictionary learning · Image inpainting, cropped region visual comparison | PSNR (dB): 6.24 -> 12.65 | Improved |
Closest papers by meaning
- Online Convolutional Sparse Coding with Sample-Dependent Dictionary (ICML 2018 · similarity 0.92)
- A Local Block Coordinate Descent Algorithm for the CSC Model (CVPR 2019 · similarity 0.92)
- Rethinking the CSC Model for Natural Images (NeurIPS 2019 · similarity 0.91)
- Consensus Convolutional Sparse Coding (ICCV 2017 · similarity 0.91)
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens (ICLR 2024 · similarity 0.86)
- Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once (ICML 2024 · similarity 0.86)
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.
