Revisiting Multiple Instance Neural Networks

TL;DR

This paper revisits multiple instance learning using neural networks, proposing a new approach that learns bag representations directly, incorporates deep supervision, and achieves state-of-the-art performance with high efficiency.

Contribution

Introduces a novel multiple instance neural network that learns bag representations and utilizes deep supervision, improving accuracy and speed over existing methods.

Findings

Achieves state-of-the-art or competitive results on MIL benchmarks.

Extremely fast training and testing times, e.g., 0.0003 seconds per bag.

Deep supervision significantly boosts bag classification accuracy.

Abstract

Recently neural networks and multiple instance learning are both attractive topics in Artificial Intelligence related research fields. Deep neural networks have achieved great success in supervised learning problems, and multiple instance learning as a typical weakly-supervised learning method is effective for many applications in computer vision, biometrics, nature language processing, etc. In this paper, we revisit the problem of solving multiple instance learning problems using neural networks. Neural networks are appealing for solving multiple instance learning problem. The multiple instance neural networks perform multiple instance learning in an end-to-end way, which take a bag with various number of instances as input and directly output bag label. All of the parameters in a multiple instance network are able to be optimized via back-propagation. We propose a new multiple instance neural network to learn bag representations, which is different from the existing multiple instance neural networks that focus on estimating instance label. In addition, recent tricks developed in deep learning have been studied in multiple instance networks, we find deep supervision is effective for boosting bag classification accuracy. In the experiments, the proposed multiple instance networks achieve state-of-the-art or competitive performance on several MIL benchmarks. Moreover, it is extremely fast for both testing and training, e.g., it takes only 0.0003 second to predict a bag and a few seconds to train on a MIL datasets on a moderate CPU.