Attention Awareness Multiple Instance Neural Network

TL;DR

This paper introduces an attention-aware multiple instance neural network that enhances pattern recognition by improving instance selection and bag-level representation, outperforming existing methods.

Contribution

It proposes a novel trainable MIL pooling operator based on spatial attention, addressing limitations of pre-defined pooling methods.

Findings

Outperforms state-of-the-art MIL methods in various tasks

Validates effectiveness of the proposed attention MIL pooling operator

Enhances accuracy of bag-level representations

Abstract

Multiple instance learning is qualified for many pattern recognition tasks with weakly annotated data. The combination of artificial neural network and multiple instance learning offers an end-to-end solution and has been widely utilized. However, challenges remain in two-folds. Firstly, current MIL pooling operators are usually pre-defined and lack flexibility to mine key instances. Secondly, in current solutions, the bag-level representation can be inaccurate or inaccessible. To this end, we propose an attention awareness multiple instance neural network framework in this paper. It consists of an instance-level classifier, a trainable MIL pooling operator based on spatial attention and a bag-level classification layer. Exhaustive experiments on a series of pattern recognition tasks demonstrate that our framework outperforms many state-of-the-art MIL methods and validates the effectiveness of our proposed attention MIL pooling operators.