Research map / Image generation / GANs
Learn distributed GAN with Temporary Discriminators
Hui Qu, Yikai Zhang, Qi Chang, Zhennan Yan, Chao Chen, Dimitris Metaxas
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 reminding loss (ablation) | TDGAN · Multi-Organ heterogeneous Task3 | Dice: 0.1812 -> 0.7610 | Improved |
| add reminding loss (ablation) | TDGAN · Multi-Organ heterogeneous Task2 | Dice: 0.3733 -> 0.7570 | Improved |
| add reminding loss (ablation) | TDGAN · Multi-Organ heterogeneous Task3 | AJI: 0.0240 -> 0.5028 | Improved |
| add reminding loss (ablation) | TDGAN · BraTS-T2 heterogeneous Task3 | Dice: 0.2490 -> 0.6713 | Improved |
| add reminding loss (ablation) | TDGAN · Multi-Organ single-entity Task4 (prostate) | Dice: 0.6969 -> 0.7481 | Improved |
| add reminding loss (ablation) | TDGAN · Multi-Organ multiple-entity Task2 | AJI: 0.4780 -> 0.5136 | Improved |
| add reminding loss (ablation) | TDGAN · Multi-Organ single-entity Task2 (breast) | AJI: 0.4405 -> 0.4323 | No clear effect |
| add reminding loss (ablation) | TDGAN · BraTS-T1 heterogeneous Task3 | Dice: 0.5288 -> 0.5265 | No clear effect |
| use distributed temporary discriminators instead of one joint discriminator | TDGAN · Multi-Organ heterogeneous Task3 | Dice: 0.6566 -> 0.7610 | Improved |
| use distributed temporary discriminators instead of one joint discriminator | TDGAN · BraTS-T1 heterogeneous Task3 | Dice: 0.4627 -> 0.5265 | Improved |
| use joint centralized training instead of TDGAN | TDGAN · Multi-Organ single-entity Task4 (prostate) | Dice: 0.7481 -> 0.7627 | Improved |
| learn from other entities rather than local data only | Local GAN · Multi-Organ single-entity Task4 (prostate) | Dice: 0.6918 -> 0.7481 | Improved |
Closest papers by meaning
- A Decentralized Parallel Algorithm for Training Generative Adversarial Nets (NeurIPS 2020 · similarity 0.87)
- Dynamically Masked Discriminator for GANs (NeurIPS 2023 · similarity 0.87)
- Instance-Conditioned GAN (NeurIPS 2021 · similarity 0.87)
- On-Line Adaptative Curriculum Learning for GANs (AAAI 2019 · similarity 0.86)
- Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data (CVPR 2020 · similarity 0.86)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.85)
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.
