Attention-based Deep Multiple Instance Learning

TL;DR

This paper introduces an attention-based neural network approach for multiple instance learning that models bag labels probabilistically, offers interpretability, and achieves competitive results on various datasets.

Contribution

It proposes a novel neural network permutation-invariant attention mechanism for MIL, enhancing interpretability and performance.

Findings

Achieves comparable performance to top MIL methods on benchmarks.

Outperforms existing methods on MNIST-based and histopathology datasets.

Provides interpretability by highlighting instance contributions.

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.