Deep Multi-instance Learning with Dynamic Pooling

Yongluan Yan, Xinggang Wang, Xiaojie Guo, Jiemin Fang, Wenyu Liu, Junzhou Huang
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:662-677, 2018.

Abstract

End-to-end optimization of multi-instance learning (MIL) using neural networks is an important problem with many applications, in which a core issue is how to design a permutation-invariant pooling function without losing much instance-level information. Inspired by the dynamic routing in recent capsule networks, we propose a novel dynamic pooling function for MIL. It is an adaptive scheme for both key instance selection and modeling the contextual information among instances in a bag. The dynamic pooling iteratively updates the instance contribution to its bag. It is permutation-invariant and can interpret instance-to-bag relationship. The proposed dynamic pooling based multi-instance neural network has been validated on many MIL tasks and outperforms other MIL methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-yan18a, title = {Deep Multi-instance Learning with Dynamic Pooling}, author = {Yan, Yongluan and Wang, Xinggang and Guo, Xiaojie and Fang, Jiemin and Liu, Wenyu and Huang, Junzhou}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {662--677}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/yan18a/yan18a.pdf}, url = {https://proceedings.mlr.press/v95/yan18a.html}, abstract = {End-to-end optimization of multi-instance learning (MIL) using neural networks is an important problem with many applications, in which a core issue is how to design a permutation-invariant pooling function without losing much instance-level information. Inspired by the dynamic routing in recent capsule networks, we propose a novel dynamic pooling function for MIL. It is an adaptive scheme for both key instance selection and modeling the contextual information among instances in a bag. The dynamic pooling iteratively updates the instance contribution to its bag. It is permutation-invariant and can interpret instance-to-bag relationship. The proposed dynamic pooling based multi-instance neural network has been validated on many MIL tasks and outperforms other MIL methods.} }
Endnote
%0 Conference Paper %T Deep Multi-instance Learning with Dynamic Pooling %A Yongluan Yan %A Xinggang Wang %A Xiaojie Guo %A Jiemin Fang %A Wenyu Liu %A Junzhou Huang %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-yan18a %I PMLR %P 662--677 %U https://proceedings.mlr.press/v95/yan18a.html %V 95 %X End-to-end optimization of multi-instance learning (MIL) using neural networks is an important problem with many applications, in which a core issue is how to design a permutation-invariant pooling function without losing much instance-level information. Inspired by the dynamic routing in recent capsule networks, we propose a novel dynamic pooling function for MIL. It is an adaptive scheme for both key instance selection and modeling the contextual information among instances in a bag. The dynamic pooling iteratively updates the instance contribution to its bag. It is permutation-invariant and can interpret instance-to-bag relationship. The proposed dynamic pooling based multi-instance neural network has been validated on many MIL tasks and outperforms other MIL methods.
APA
Yan, Y., Wang, X., Guo, X., Fang, J., Liu, W. & Huang, J.. (2018). Deep Multi-instance Learning with Dynamic Pooling. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:662-677 Available from https://proceedings.mlr.press/v95/yan18a.html.

Related Material