Attention-based Deep Multiple Instance Learning

by   Maximilian Ilse, et al.

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.


page 7

page 8

page 14

page 15

page 16


Certainty Pooling for Multiple Instance Learning

Multiple Instance Learning is a form of weakly supervised learning in wh...

Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning

Multiple Instance Learning (MIL) involves predicting a single label for ...

Dual-stream Maximum Self-attention Multi-instance Learning

Multi-instance learning (MIL) is a form of weakly supervised learning wh...

Revisiting Multiple Instance Neural Networks

Recently neural networks and multiple instance learning are both attract...

Model Agnostic Interpretability for Multiple Instance Learning

In Multiple Instance Learning (MIL), models are trained using bags of in...

Deep Instance-Level Hard Negative Mining Model for Histopathology Images

Histopathology image analysis can be considered as a Multiple instance l...

Code Repositories


Implementation of Attention-based Deep Multiple Instance Learning in PyTorch

view repo

Please sign up or login with your details

Forgot password? Click here to reset