Research map / Image generation / Autoregressive and latent generation
Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation
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 |
|---|---|---|---|
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut crack | KID: 24.69 -> 19.73 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut cut | KID: 19.84 -> 16.88 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut hole | KID: 22.43 -> 20.78 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut print | KID: 28.75 -> 27.25 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut crack | LPIPS: 0.1905 -> 0.2600 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut cut | LPIPS: 0.2045 -> 0.2073 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut hole | LPIPS: 0.2108 -> 0.2391 | Helped |
| Use DFMGAN instead of the strongest listed baseline | Few-shot defect generation · Hazelnut print | LPIPS: 0.2185 -> 0.2649 | Helped |
| Train the classifier using DFMGAN-generated augmentation rather than the strongest listed baseline augmentation | Hazelnut defect classification · Hazelnut P1 | accuracy: 70.83 -> 83.33 | Helped |
| Train the classifier using DFMGAN-generated augmentation rather than the strongest listed baseline augmentation | Hazelnut defect classification · Hazelnut P2 | accuracy: 72.91 -> 81.25 | Helped |
| Train the classifier using DFMGAN-generated augmentation rather than the strongest listed baseline augmentation | Hazelnut defect classification · Hazelnut P3 | accuracy: 68.75 -> 81.25 | Helped |
Closest papers by meaning
- DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection (CVPR 2025 · similarity 0.91)
- Exploring the Relationship Between Samples and Masks for Robust Defect Localization (AAAI 2025 · similarity 0.88)
- MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-Context (AAAI 2025 · similarity 0.87)
- Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection (CVPR 2025 · similarity 0.86)
- Automated Defect Report Generation for Enhanced Industrial Quality Control (AAAI 2024 · similarity 0.84)
- AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model (AAAI 2024 · similarity 0.84)
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.