Research map / Label-efficient and robust learning / Recognition and long-tail
[Re] Solving Phase Retrieval With a Learned Reference
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace the strongest listed baseline, Random Reference, with a learned reference | Fourier phase retrieval · MNIST | PSNR: 36.87 -> 66.54 | Helped |
| replace the strongest listed baseline, Random Reference, with a learned reference | Fourier phase retrieval · EMNIST | PSNR: 28.41 -> 58.72 | Helped |
| replace the strongest listed baseline, Random Reference, with a learned reference | Fourier phase retrieval · Fashion MNIST | PSNR: 27.27 -> 57.81 | Helped |
| replace the strongest listed baseline, Random Reference, with a learned reference | Fourier phase retrieval · SVHN | PSNR: 36.45 -> 57.51 | Helped |
| replace the strongest listed baseline, Random Reference, with a learned reference | Fourier phase retrieval · CIFAR10 | PSNR: 25.57 -> 41.60 | Helped |
| increase training set size from 32 to 512 images (ablation) | Learned Reference · MNIST | PSNR: 66.54 -> 79.14 | Helped |
| increase training set size from 32 to 512 images (ablation) | Learned Reference · EMNIST | PSNR: 58.72 -> 62.34 | Helped |
| increase training set size from 32 to 512 images (ablation) | Learned Reference · Fashion MNIST | PSNR: 57.81 -> 52.01 | Hurt |
| increase training set size from 32 to 512 images (ablation) | Learned Reference · SVHN | PSNR: 57.51 -> 59.78 | Helped |
| increase training set size from 32 to 512 images (ablation) | Learned Reference · CIFAR10 | PSNR: 41.60 -> 48.90 | Helped |
| increase the number of unrolled iterations K (ablation) | Learned Reference · Fourier phase retrieval | PSNR | Helped |
| increase test-time K beyond a point (ablation) | Learned Reference · Fourier phase retrieval | PSNR | No clear effect |
Closest papers by meaning
- Fast, Sample-Efficient Algorithms for Structured Phase Retrieval (NeurIPS 2017 · similarity 0.90)
- Convex Phase Retrieval without Lifting via PhaseMax (ICML 2017 · similarity 0.88)
- Unsupervised Deep Learning for Phase Retrieval via Teacher-Student Distillation (AAAI 2023 · similarity 0.86)
- Phase Retrieval Under a Generative Prior (NeurIPS 2018 · similarity 0.86)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.85)
- Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval (ICML 2024 · similarity 0.83)
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.