Research map / Image generation / Super-resolution
PyraE2E: Enhancing End-to-End WSI Analysis via Cross-Scale Super-Resolution
Yuechuan Lin, yujian liu, Weipeng Zhang, Yanyu Fan, Zikang Wang, Dongxu Shen, Liqin Fei, Xiaoli Liu, Shidang Xu
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 SR-based self-supervision and GLP encoder versus E2E ABMILX baseline | E2E ABMILX · TCGA-NSCLC | ACC: 90.2±1.0 -> 92.0±1.4 | Improved |
| PyraE2E-X versus UNI ABMIL on TCGA-BRCA | PyraE2E · TCGA-BRCA | ACC: 91.2±0.5 vs 90.5±1.3 | Hurt |
| use cluster + attention embedded sampling versus random (ablation) | PyraE2E · TCGA-NSCLC | ACC: 89.9±0.8 -> 92.0±1.4 | Improved |
| use embedded versus external attention sampling (ablation) | PyraE2E · TCGA-NSCLC | ACC: 91.1±1.0 -> 92.0±1.4 | Improved |
| add frequency-domain (FFT) SR loss (ablation) | PyraE2E · TCGA-NSCLC | ACC: 86.2±1.8 -> 92.0±1.4 | Improved |
| add cluster-wise KLD attention regularizer (ablation) | PyraE2E · TCGA-NSCLC | ACC: 90.5±1.4 -> 92.0±1.4 | Improved |
| scale SR loss weights 0.5x to 2x (ablation) | PyraE2E · TCGA-NSCLC | ACC: 91.2±1.3 / 92.0±1.4 / 91.8±1.2 | No clear effect |
| PyraE2E versus SimCLR/CDSR self-supervised pipelines on cost | PyraE2E · TCGA-NSCLC | training time: 1.1d vs 6.4d (SimCLR), 2.1d (CDSR) | Improved |
| PyraE2E-X versus baselines on TCGA-RCC AUC | PyraE2E · TCGA-RCC | AUC: 98.3±0.2 vs 98.0±0.2 (C2C), 99.1±0.1 (UNI) | Mixed |
Closest papers by meaning
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.88)
- FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification (NeurIPS 2024 · similarity 0.86)
- Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis (NeurIPS 2024 · similarity 0.86)
- CaMIL: Causal Multiple Instance Learning for Whole Slide Image Classification (AAAI 2024 · similarity 0.86)
- FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification (CVPR 2025 · similarity 0.86)
- MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding (CVPR 2026 · similarity 0.86)
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.
