Research map / Label-efficient and robust learning / Recognition and long-tail
RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced Categories
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 |
|---|---|---|---|
| Add RankMix with self-training to DSMIL | DSMIL · Camelyon16 | ACC: 86.82% -> 89.92% | Helped |
| Add RankMix with self-training to DSMIL | DSMIL · WSI-usability | ACC: 76.11% -> 90.27% | Helped |
| Add RankMix with self-training to DSMIL | DSMIL · TCGA-Lung | ACC: 93.81% -> 94.29% | Helped |
| Add RankMix with self-training to FRMIL | FRMIL · Camelyon16 | ACC: 89.15% -> 91.47% | Helped |
| Add RankMix with self-training to FRMIL | FRMIL · WSI-usability | ACC: 83.19% -> 93.81% | Helped |
| Add RankMix with self-training to FRMIL | FRMIL · TCGA-Lung | ACC: 90.95% -> 93.33% | Helped |
| Add self-training to RankMix (ablation) | DSMIL + RankMix · Camelyon16 | ACC: 87.60% -> 89.92% | Helped |
| Add self-training to RankMix (ablation) | DSMIL + RankMix · WSI-usability | ACC: 90.27% -> 90.27% | No clear effect |
| Add self-training to RankMix (ablation) | FRMIL + RankMix · WSI-usability | ACC: 80.53% -> 93.81% | Helped |
| Use RankMix instead of ReMix | DSMIL augmentation · WSI-usability | ACC: 83.19% -> 90.27% | Helped |
| Use RankMix instead of Direct Mixup | DSMIL augmentation · Camelyon16 | ACC: 84.50% -> 89.92% | Helped |
| Use RankMix instead of Shrink Mixup | FRMIL augmentation · WSI-usability | AUC: 57.09% -> 93.61% | Helped |
Closest papers by meaning
- MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification (CVPR 2025 · similarity 0.87)
- FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification (NeurIPS 2024 · similarity 0.85)
- Promptable Representation Distribution Learning and Data Augmentation for Gigapixel Histopathology WSI Analysis (AAAI 2025 · similarity 0.83)
- Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference (AAAI 2024 · similarity 0.83)
- OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual Learning (AAAI 2025 · similarity 0.82)
- Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification (AAAI 2025 · 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.