Attention-based deep multiple instance learning

Maximilian Ilse*, Jakub M. Tomczak, Max Welling

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we propose a neural network-based permutation-invariant aggregation operator that corresponds to the attention mechanism. Notably, an application of the proposed attention-based operator provides insight into the contribution of each instance to the bag label. We show empirically that our approach achieves comparable performance to the best MIL methods on benchmark MIL datasets and it outperforms other methods on a MNIST-based MIL dataset and two real-life histopathology datasets without sacrificing interpretability.

Original languageEnglish
Title of host publication35th International Conference on Machine Learning, ICML 2018
EditorsJennifer Dy, Andreas Krause
PublisherInternational Machine Learning Society (IMLS)
Pages3376-3391
Number of pages16
ISBN (Electronic)9781510867963
Publication statusPublished - 1 Jan 2018
Externally publishedYes
Event35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden
Duration: 10 Jul 201815 Jul 2018

Publication series

Name35th International Conference on Machine Learning, ICML 2018
Volume5

Conference

Conference35th International Conference on Machine Learning, ICML 2018
CountrySweden
CityStockholm
Period10/07/1815/07/18

Fingerprint Dive into the research topics of 'Attention-based deep multiple instance learning'. Together they form a unique fingerprint.

Cite this