Attention-based Deep Multiple Instance Learning

By Maximilian Ilse, J. Tomczak, Max Welling. 2018

2,646 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Jianfeng Gao
  3. Mohit Bansal
  4. Quoc V. Le
  5. Dacheng Tao
  6. Sergey Levine
  7. Ruslan Salakhutdinov
  8. Percy Liang

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Ming-Hsuan Yang
  4. Yi Yang
  5. Andrea Vedaldi
  6. Trevor Darrell
  7. Jitendra Malik
  8. Xiaogang Wang

In Medical Imaging

  1. Fanjie Kong
  2. Ricardo Henao
  3. Faisal Mahmood
  4. Tiffany Y. Chen
  5. Ming Y. Lu
  6. Drew F. K. Williamson
  7. Richard J. Chen
  8. Anne L. Martel

Citations in the corpus