Research map / Label-efficient and robust learning / Recognition and long-tail
SCL-WC: Cross-Slide Contrastive Learning for Weakly-Supervised Whole-Slide Image Classification
Xiyue Wang, Jinxi Xiang, Jun Zhang, Sen Yang, Zhongyi Yang, Ming-Hui Wang, Jing Zhang, Yang Wei, Junzhou Huang, Xiao Han
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 |
|---|---|---|---|
| SSL histopathology-pretrained extractor instead of ImageNet (ablation) | SCL-WC · Camelyon16 | AUC: 0.8730 -> 0.9080 | Improved |
| SSL histopathology-pretrained extractor instead of ImageNet (ablation) | SCL-WC · BRACS | AUC: 0.8114 -> 0.8335 | Improved |
| add positive-negative-aware loss (PNM) (ablation) | SCL-WC · Camelyon16 | AUC: 0.9080 -> 0.9190 | Improved |
| add positive-negative-aware loss (PNM) (ablation) | SCL-WC · BRACS | AUC: 0.8335 -> 0.8403 | Improved |
| add WSCL without hard negatives (ablation) | SCL-WC · Camelyon16 | AUC: 0.9190 -> 0.9330 | Improved |
| add hard negative samples to WSCL (ablation) | SCL-WC · Camelyon16 | AUC: 0.9330 -> 0.9566 | Improved |
| add hard negative samples to WSCL (ablation) | SCL-WC · BRACS | AUC: 0.8512 -> 0.8650 | Improved |
| our aggregator instead of CLAM aggregator (ablation) | SCL-WC · TCGA-CRC-DX (own extractor) | AUC: 0.8530 -> 0.8954 | Improved |
| our extractor instead of DINO-ViT (ablation) | SCL-WC · TCGA-CRC-DX | AUC: 0.8246 -> 0.8954 | Improved |
| our aggregator instead of CLAM aggregator | SCL-WC · BRACS (ImageNet extractor) | AUC: 0.8158 -> 0.8446 | Improved |
| SCL-WC versus TransMIL | SCL-WC · Camelyon16 | AUC: 0.9337 -> 0.9566 | Improved |
| SCL-WC versus CLAM | SCL-WC · PANDA | ACC: 0.8874 -> 0.9194 | 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.
- TransMIL — TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification (NeurIPS 2021) · better on 4 of 4 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
- FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification (NeurIPS 2024 · similarity 0.88)
- CaMIL: Causal Multiple Instance Learning for Whole Slide Image Classification (AAAI 2024 · similarity 0.88)
- Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification (AAAI 2025 · similarity 0.88)
- Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction (CVPR 2024 · similarity 0.87)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 2025 · similarity 0.86)
- Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification (CVPR 2024 · 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.
