Research map / Image generation / GANs
Ph-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data
Xidan Zhang, Yihan Zhuang, Qian Guo, Haodong Yang, Xuelin Qian, Gong Cheng, Junwei Han, Zhongling Huang
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 physics-inspired regularization (PSC losses) | ACGAN · 10% MSTAR | FID: 290.0484 -> 87.2719 | Improved |
| add physics-inspired regularization (PSC losses) | ACGAN · 5% MSTAR | FID: 340.2440 -> 130.2311 | Improved |
| add physics-inspired regularization | StyleGAN · 10% MSTAR | FID: 290.6406 -> 174.8329 | Improved |
| add physics-inspired regularization | StyleGAN · 1% OpenSARShip | FID: 45.0999 -> 44.7829 | No clear effect |
| add physics-inspired regularization | CVAE-GAN · 1% OpenSARShip | FID: 23.9480 -> 15.0530 | Improved |
| add DiffAugment (DA) to ACGAN | ACGAN · 10% MSTAR | FID: 290.0484 -> 1089.4734 | Hurt |
| add ADA to ACGAN | ACGAN · 10% MSTAR | FID: 290.0484 -> 320.5937 | Hurt |
| add DIG to ACGAN | ACGAN · 5% MSTAR | FID: 340.2440 -> 438.7845 | Hurt |
| add image-level generator physical loss (ablation) | ACGAN · 10% MSTAR | FID: 290.0484 -> 97.4472 | Improved |
| add discriminator physical loss alone (ablation) | ACGAN · 10% MSTAR | FID: 290.0484 -> 92.7562 | Improved |
| add discriminator loss to generator physical losses (ablation) | ACGAN · 10% MSTAR | FID: 177.1856 -> 87.2719 | Improved |
| add image-level generator loss to feature-level generator and discriminator losses (ablation) | ACGAN · 10% MSTAR | FID: 95.9290 -> 87.2719 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CVAE-GAN — CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training (ICCV 2017) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Statistically Principled Deep Learning for SAR Image Segmentation (AAAI 2024 · similarity 0.82)
- WeditGAN: Few-Shot Image Generation via Latent Space Relocation (AAAI 2024 · similarity 0.80)
- SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection (NeurIPS 2024 · similarity 0.80)
- Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition (ICML 2025 · similarity 0.80)
- SMaRt: Improving GANs with Score Matching Regularity (ICML 2024 · similarity 0.80)
- Uncertainty-Aware GAN for Single Image Super Resolution (AAAI 2024 · similarity 0.80)
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.
