Research map / Label-efficient and robust learning / Recognition and long-tail
Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology
Syed Ashar Javed, Dinkar Juyal, Harshith Padigela, Amaro Taylor-Weiner, Limin Yu, aaditya prakash
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 |
|---|---|---|---|
| Make attention MIL additive | Attention MIL (ABMIL) · Camelyon16 | AUC: 0.750 -> 0.846 | Improved |
| Make attention MIL additive | Attention MIL (ABMIL) · Camelyon16 | accuracy: 0.773 -> 0.830 | Improved |
| Make attention MIL additive | Attention MIL (ABMIL) · TCGA RCC | accuracy: 0.878 -> 0.915 | Improved |
| Make attention MIL additive | Attention MIL (ABMIL) · TCGA NSCLC | AUC: 0.946 -> 0.941 | No clear effect |
| Make TransMIL additive | TransMIL · Camelyon16 | AUC: 0.775 -> 0.844 | Improved |
| Make TransMIL additive | TransMIL · Camelyon16 | accuracy: 0.805 -> 0.805 | No clear effect |
| Make TransMIL additive | TransMIL · TCGA NSCLC | accuracy: 0.878 -> 0.895 | Improved |
| Make TransMIL additive | TransMIL · TCGA RCC | accuracy: 0.915 -> 0.911 | No clear effect |
| Make mean pooling MIL additive | Mean Pooling MIL · Camelyon16 | AUC: 0.707 -> 0.687 | Hurt |
| Make mean pooling MIL additive | Mean Pooling MIL · TCGA NSCLC | accuracy: 0.830 -> 0.866 | Improved |
| Make mean pooling MIL additive | Mean Pooling MIL · TCGA RCC | accuracy: 0.918 -> 0.902 | Hurt |
| Use patch contribution heatmap instead of attention heatmap from the same model | Additive MIL · Camelyon16 region annotations | AUPRC: 0.36 -> 0.42 | 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 5 of 6 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
- Do Multiple Instance Learning Models Transfer? (ICML 2025 · similarity 0.91)
- xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology (NeurIPS 2024 · similarity 0.90)
- Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology (NeurIPS 2026 · similarity 0.89)
- SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology (CVPR 2024 · similarity 0.89)
- Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology (CVPR 2024 · similarity 0.89)
- Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology (NeurIPS 2025 · similarity 0.87)
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.
