# Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning

arXiv: https://arxiv.org/abs/2302.04061 · HTML: https://mlsanity.com/paper/2302.04061/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 8 Feb 2023.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [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)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Scalable Variational Gaussian Process Classification](https://mlsanity.com/paper/1411.2005/) (2014)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [When Gaussian Process Meets Big Data: A Review of Scalable GPs](https://mlsanity.com/paper/1807.01065/) (2018)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection](https://mlsanity.com/paper/2105.10490/) (2021)
- [Applications of Deep Learning and Reinforcement Learning to Biological Data](https://mlsanity.com/paper/1711.03985/) (2017)
- [Weakly Labelled AudioSet Tagging with Attention Neural Networks](https://mlsanity.com/paper/1903.00765/) (2019)
- [Overcoming the limitations of patch-based learning to detect cancer in whole slide images](https://mlsanity.com/paper/2012.00617/) (2020)
- [Self-learning for weakly supervised Gleason grading of local patterns](https://mlsanity.com/paper/2105.10420/) (2021)
- [GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention](https://mlsanity.com/paper/2003.04575/) (2020)
- [Remote Sensing Image Classification with Large Scale Gaussian Processes](https://mlsanity.com/paper/1710.00575/) (2017)
- [Deep Gaussian Processes for Biogeophysical Parameter Retrieval and Model Inversion](https://mlsanity.com/paper/2104.10638/) (2021)
- [Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO](https://mlsanity.com/paper/1911.01915/) (2019)
- [Attentive Gaussian processes for probabilistic time-series generation](https://mlsanity.com/paper/2102.05208/) (2021)

## Built on by (most cited first, 8 of 8)

- [Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation](https://mlsanity.com/paper/2307.11397/) (2023)
- [Sparsity-Aware Distributed Learning for Gaussian Processes with Linear Multiple Kernel](https://mlsanity.com/paper/2309.08201/) (2023)
- [SGPMIL: Sparse Gaussian Process Multiple Instance Learning](https://mlsanity.com/paper/2507.08711/) (2025)
- [Deep Transformed Gaussian Processes](https://mlsanity.com/paper/2310.18230/) (2023)
- [Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images](https://mlsanity.com/paper/2310.19359/) (2023)
- [Multiple Instance Learning with Trainable Decision Tree Ensembles](https://mlsanity.com/paper/2302.06601/) (2023)
- [On the detection of Out-Of-Distribution samples in Multiple Instance Learning](https://mlsanity.com/paper/2309.05528/) (2023)
- [Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Images](https://mlsanity.com/paper/2405.15264/) (2024)

## Abstract (arXiv)

Multiple Instance Learning (MIL) is a weakly supervised learning paradigm that is becoming increasingly popular because it requires less labeling effort than fully supervised methods. This is especially interesting for areas where the creation of large annotated datasets remains challenging, as in medicine. Although recent deep learning MIL approaches have obtained state-of-the-art results, they are fully deterministic and do not provide uncertainty estimations for the predictions. In this work, we introduce the Attention Gaussian Process (AGP) model, a novel probabilistic attention mechanism based on Gaussian Processes for deep MIL. AGP provides accurate bag-level predictions as well as instance-level explainability, and can be trained end-to-end. Moreover, its probabilistic nature guarantees robustness to overfitting on small datasets and uncertainty estimations for the predictions. The latter is especially important in medical applications, where decisions have a direct impact on the patient's health. The proposed model is validated experimentally as follows. First, its behavior is illustrated in two synthetic MIL experiments based on the well-known MNIST and CIFAR-10 datasets, respectively. Then, it is evaluated in three different real-world cancer detection experiments. AGP outperforms state-of-the-art MIL approaches, including deterministic deep learning ones. It shows a strong performance even on a small dataset with less than 100 labels and generalizes better than competing methods on an external test set. Moreover, we experimentally show that predictive uncertainty correlates with the risk of wrong predictions, and therefore it is a good indicator of reliability in practice. Our code is publicly available.