Kernel Self-Attention in Deep Multiple Instance Learning

TL;DR

This paper introduces a novel self-attention based pooling method for multiple instance learning that models dependencies within bags of instances, demonstrating improved performance across various datasets.

Contribution

The paper proposes SA-AbMILP, a new self-attention pooling method for MIL that accounts for dependencies between instances, unlike previous models.

Findings

SA-AbMILP outperforms existing MIL models on multiple datasets.

Kernel variations of self-attention influence model performance.

Model effectively captures dependencies within bags of instances.

Abstract

Not all supervised learning problems are described by a pair of a fixed-size input tensor and a label. In some cases, especially in medical image analysis, a label corresponds to a bag of instances (e.g. image patches), and to classify such bag, aggregation of information from all of the instances is needed. There have been several attempts to create a model working with a bag of instances, however, they are assuming that there are no dependencies within the bag and the label is connected to at least one instance. In this work, we introduce Self-Attention Attention-based MIL Pooling (SA-AbMILP) aggregation operation to account for the dependencies between instances. We conduct several experiments on MNIST, histological, microbiological, and retinal databases to show that SA-AbMILP performs better than other models. Additionally, we investigate kernel variations of Self-Attention and their influence on the results.