# Nested Multiple Instance Learning with Attention Mechanisms

arXiv: https://arxiv.org/abs/2111.00947 · HTML: https://mlsanity.com/paper/2111.00947/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 13 of 13)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Rotation Equivariant CNNs for Digital Pathology](https://mlsanity.com/paper/1806.03962/) (2018)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2103.10626/) (2021)
- [A Multi-resolution Model for Histopathology Image Classification and Localization with Multiple Instance Learning](https://mlsanity.com/paper/2011.02679/) (2020)
- [Channel Attention Residual U-Net for Retinal Vessel Segmentation](https://mlsanity.com/paper/2004.03702/) (2020)
- [Learning and Interpreting Multi-Multi-Instance Learning Networks](https://mlsanity.com/paper/1810.11514/) (2018)

## Built on by (most cited first, 7 of 7)

- [Model Agnostic Interpretability for Multiple Instance Learning](https://mlsanity.com/paper/2201.11701/) (2022)
- [Semantic Communications for Artificial Intelligence Generated Content (AIGC) Toward Effective Content Creation](https://mlsanity.com/paper/2308.04942/) (2023)
- [Multi-Attention Multiple Instance Learning](https://mlsanity.com/paper/2112.06071/) (2021)
- [Towards Hierarchical Regional Transformer-based Multiple Instance Learning](https://mlsanity.com/paper/2308.12634/) (2023)
- [Multiple Instance Learning with Trainable Decision Tree Ensembles](https://mlsanity.com/paper/2302.06601/) (2023)
- [Self-Contrastive Weakly Supervised Learning Framework for Prognostic Prediction Using Whole Slide Images](https://mlsanity.com/paper/2405.15264/) (2024)
- [NMGrad: Advancing Histopathological Bladder Cancer Grading with Weakly Supervised Deep Learning](https://mlsanity.com/paper/2405.15275/) (2024)

## Abstract (arXiv)

Strongly supervised learning requires detailed knowledge of truth labels at instance levels, and in many machine learning applications this is a major drawback. Multiple instance learning (MIL) is a popular weakly supervised learning method where truth labels are not available at instance level, but only at bag-of-instances level. However, sometimes the nature of the problem requires a more complex description, where a nested architecture of bag-of-bags at different levels can capture underlying relationships, like similar instances grouped together. Predicting the latent labels of instances or inner-bags might be as important as predicting the final bag-of-bags label but is lost in a straightforward nested setting. We propose a Nested Multiple Instance with Attention (NMIA) model architecture combining the concept of nesting with attention mechanisms. We show that NMIA performs as conventional MIL in simple scenarios and can grasp a complex scenario providing insights to the latent labels at different levels.