Research map / Label-efficient and robust learning / Recognition and long-tail
G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification
Bingzhe Wu, Xiaolu Zhang, Shiwan Zhao, Lingxi Xie, Caihong Zeng, Zhihong Liu, Guangyu Sun
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 generated H&E, MASSON, and PASM to PAS input | PAS_ONLY · Glomerulus s-vs-noa | Average accuracy (%): 90.74 -> 93.34 | Improved |
| Add generated H&E, MASSON, and PASM to PAS input | PAS_ONLY · Glomerulus ss-vs-gs | Average accuracy (%): 87.41 -> 89.90 | Improved |
| Add generated H&E only | PAS_ONLY · Glomerulus s-vs-noa | Average accuracy (%): 90.74 -> 92.55 | Improved |
| Add generated MASSON only | PAS_ONLY · Glomerulus s-vs-noa | Average accuracy (%): 90.74 -> 92.06 | Improved |
| Add generated PASM only | PAS_ONLY · Glomerulus ss-vs-gs | Average accuracy (%): 87.41 -> 89.50 | Improved |
| Add cross-stain attention (ablation) | PAS_ALL · Glomerulus s-vs-noa | Average accuracy (%): 93.34 -> 93.68 | Improved |
| Add cross-stain attention (ablation) | PAS_ALL · Glomerulus ss-vs-gs | Average accuracy (%): 89.90 -> 90.45 | Improved |
| Jointly fine-tune generators and classifier instead of freezing generators (ablation) | PAS_ALL · Glomerulus s-vs-noa | Average accuracy (%): +1.10% | Improved |
| Jointly fine-tune generators and classifier instead of freezing generators (ablation) | PAS_ALL · Glomerulus ss-vs-gs | Average accuracy (%): +1.54% | Improved |
| Add cross-stain attention to PAS_ONLY (ablation) | PAS_ONLY · Glomerulus s-vs-noa | Overall accuracy (%): +0.30% | Improved |
| Add cross-stain attention to PAS_ONLY (ablation) | PAS_ONLY · Glomerulus ss-vs-gs | Overall accuracy (%): +0.09% | Improved |
| Use cross-stain generation and attention instead of conventional data augmentation (ablation) | PAS_ONLY · Glomerulus ss-vs-gs | Accuracy (%): 86.21% -> 90.45% | Improved |
Closest papers by meaning
- PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation (CVPR 2024 · similarity 0.86)
- Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework (CVPR 2024 · similarity 0.82)
- One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation (NeurIPS 2024 · similarity 0.82)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.82)
- Cell Graph Transformer for Nuclei Classification (AAAI 2024 · similarity 0.82)
- MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays (NeurIPS 2026 · 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.
