Research map / Adversarial robustness and security / Attacks on text and graphs
MRI Banding Removal via Adversarial Training
Aaron Defazio, Tullie Murrell, Michael Recht
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 |
|---|---|---|---|
| Add orientation-adversarial training (ablation) | Standard MRI reconstruction · Radiologist banding-removal ranking | average rank: 1.43 -> 2.83 | Improved |
| Add orientation-adversarial training (ablation) | Standard MRI reconstruction · Radiologist detail-retention ranking | average rank: 2.32 -> 2.18 | No clear effect |
| Apply anisotropic blurring and adaptive noise | Standard MRI reconstruction · Radiologist banding-removal ranking | average rank: 1.43 -> 1.74 | Improved |
| Apply anisotropic blurring and adaptive noise | Standard MRI reconstruction · Radiologist detail-retention ranking | average rank: 2.32 -> 1.5 | Hurt |
| Add orientation-adversarial training (ablation) | Standard MRI reconstruction · Radiologist banding presence | fraction reporting banding present: 0.967 (0.92-1) -> 0.725 (0.62-0.82) | Improved |
Closest papers by meaning
- Training-Free Adversarial Robustness in Computational MRI (ICML 2026 · similarity 0.86)
- Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain (ICML 2025 · similarity 0.83)
- Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model (AAAI 2025 · similarity 0.83)
- Improving Deep Learning for Accelerated MRI With Data Filtering (NeurIPS 2025 · similarity 0.83)
- UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights (NeurIPS 2025 · similarity 0.82)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.82)
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.
