← Back to papers
2018 ACML ACML 2018

Deep Multi-instance Learning with Dynamic Pooling

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.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — bag-level classification
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Natural Language Processing, Reinforcement Learning, Speech & Audio

Authors

Yongluan Yan , Xinggang Wang , Xiaojie Guo , Jiemin Fang , Wenyu Liu , Junzhou Huang

Topics

Machine Learning > Core Methods > Classification Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks Machine Learning > Learning Types > Multi-Task Learning Machine Learning > Core Methods > Feature Learning Deep Learning > Learning Types > Representation Learning

Keywords

multi-instance learning dynamic pooling bag-level classification permutation-invariant pooling instance-level information
Download PDF

Related papers

Unsupervised Heterogeneous Domain Adaptation with Sparse Feature Transformation 2018
Structured Gaussian Processes with Twin Multiple Kernel Learning 2018
Discriminative Feature Representation for Person Re-identification by Batch-contrastive Loss 2018
Adversarial TableQA: Attention Supervision for Question Answering on Tables 2018
Who Are Raising Their Hands? Hand-Raiser Seeking Based on Object Detection and Pose Estimation 2018