# cDP-MIL: Robust Multiple Instance Learning via Cascaded Dirichlet Process

arXiv: https://arxiv.org/abs/2407.11448 · HTML: https://mlsanity.com/paper/2407.11448/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 58 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://mlsanity.com/paper/1802.07191/) (2018)
- [Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision](https://mlsanity.com/paper/1906.01620/) (2019)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [A graph-transformer for whole slide image classification](https://mlsanity.com/paper/2205.09671/) (2022)
- [DeepDPM: Deep Clustering With an Unknown Number of Clusters](https://mlsanity.com/paper/2203.14309/) (2022)
- [Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning](https://mlsanity.com/paper/2307.04189/) (2023)
- [ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification](https://mlsanity.com/paper/2207.01805/) (2022)
- [RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification](https://mlsanity.com/paper/2010.06440/) (2020)
- [Deep Continuous Clustering](https://mlsanity.com/paper/1803.01449/) (2018)
- [Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2206.09293/) (2022)
- [Spectral Clustering with Graph Neural Networks for Graph Pooling](https://mlsanity.com/paper/1907.00481/) (2019)
- [DSCA: A Dual-Stream Network with Cross-Attention on Whole-Slide Image Pyramids for Cancer Prognosis](https://mlsanity.com/paper/2206.05782/) (2022)
- [MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis](https://mlsanity.com/paper/2302.10574/) (2023)
- [Source-Aware Embedding Training on Heterogeneous Information Networks](https://mlsanity.com/paper/2307.04336/) (2023)
- [On the Variational Posterior of Dirichlet Process Deep Latent Gaussian Mixture Models](https://mlsanity.com/paper/2006.08993/) (2020)

## Built on by (most cited first, 5 of 5)

- [PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis](https://mlsanity.com/paper/2507.18848/) (2025)
- [Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis](https://mlsanity.com/paper/2507.02395/) (2025)
- [STAMP: Multi-pattern Attention-aware Multiple Instance Learning for STAS Diagnosis in Multi-center Histopathology Images](https://mlsanity.com/paper/2508.10473/) (2025)
- [Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation](https://mlsanity.com/paper/2511.01304/) (2025)
- [MacNet: An End-to-End Manifold-Constrained Adaptive Clustering Network for Interpretable Whole Slide Image Classification](https://mlsanity.com/paper/2602.14509/) (2026)

## Abstract (arXiv)

Multiple instance learning (MIL) has been extensively applied to whole slide histopathology image (WSI) analysis. The existing aggregation strategy in MIL, which primarily relies on the first-order distance (e.g., mean difference) between instances, fails to accurately approximate the true feature distribution of each instance, leading to biased slide-level representations. Moreover, the scarcity of WSI observations easily leads to model overfitting, resulting in unstable testing performance and limited generalizability. To tackle these challenges, we propose a new Bayesian nonparametric framework for multiple instance learning, which adopts a cascade of Dirichlet processes (cDP) to incorporate the instance-to-bag characteristic of the WSIs. We perform feature aggregation based on the latent clusters formed by the Dirichlet process, which incorporates the covariances of the patch features and forms more representative clusters. We then perform bag-level prediction with another Dirichlet process model on the bags, which imposes a natural regularization on learning to prevent overfitting and enhance generalizability. Moreover, as a Bayesian nonparametric method, the cDP model can accurately generate posterior uncertainty, which allows for the detection of outlier samples and tumor localization. Extensive experiments on five WSI benchmarks validate the superior performance of our method, as well as its generalizability and ability to estimate uncertainties. Codes are available at https://github.com/HKU-MedAI/cDPMIL.