Attention-based Deep Multiple Instance Learning

Maximilian Ilse, Jakub Tomczak, Max Welling
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:2127-2136, 2018.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-ilse18a, title = {Attention-based Deep Multiple Instance Learning}, author = {Ilse, Maximilian and Tomczak, Jakub and Welling, Max}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {2127--2136}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/ilse18a/ilse18a.pdf}, url = {https://proceedings.mlr.press/v80/ilse18a.html}, 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.} }
Endnote
%0 Conference Paper %T Attention-based Deep Multiple Instance Learning %A Maximilian Ilse %A Jakub Tomczak %A Max Welling %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-ilse18a %I PMLR %P 2127--2136 %U https://proceedings.mlr.press/v80/ilse18a.html %V 80 %X 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.
APA
Ilse, M., Tomczak, J. & Welling, M.. (2018). Attention-based Deep Multiple Instance Learning. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:2127-2136 Available from https://proceedings.mlr.press/v80/ilse18a.html.

Related Material