Research map / Image generation / Fast diffusion sampling
Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification
Xinrui Zhou, Yuhao Huang, Haoran Dou, Shijing Chen, Ao Chang, Jia Liu, Weiran Long, Jian Zheng, Erjiao Xu, Jie Ren, Alejandro Federico Frangi, Ruobing Huang and 4 more
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 Ctrl-GenAug synthetic clips (real-finetune) | I3D · Carotid | accuracy: 79.59 -> 85.03 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | I3D · TUSC | accuracy: 60.72 -> 65.41 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | I3D · ACDC | accuracy: 83.49 -> 87.16 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | I3D · MosMedData | accuracy: 67.18 -> 72.59 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | I3D · MRNet | accuracy: 63.49 -> 71.43 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | R(2+1)D · Carotid | accuracy: 82.99 -> 83.67 | No clear effect |
| add Ctrl-GenAug synthetic clips (real-finetune) | SlowFast · Carotid | accuracy: 80.95 -> 81.63 | No clear effect |
| use joint-train instead of real-finetune | CSN · Carotid | accuracy: 84.35 -> 87.07 | Improved |
| use joint-train instead of real-finetune | I3D · TUSC | accuracy: 65.41 -> 62.88 | Hurt |
| use Ctrl-GenAug instead of Mixup | I3D · Carotid | accuracy: 83.67 -> 85.03 | Improved |
| use Ctrl-GenAug instead of Endora | I3D · MRNet | accuracy: 69.31 -> 71.43 | Improved |
| add Ctrl-GenAug synthetic clips (real-finetune) | TimeSformer · MosMedData | AUROC: 0.500 -> 0.511 | No clear effect |
Closest papers by meaning
- Tokenizer-Generator Coupling in Medical Image Generation (NeurIPS 2026 · similarity 0.83)
- AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition (NeurIPS 2025 · similarity 0.83)
- Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks (ICML 2025 · similarity 0.83)
- HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation (AAAI 2025 · similarity 0.83)
- PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration (ICLR 2025 · similarity 0.83)
- PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation (AAAI 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.
