Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | 35th International Conference on Machine Learning, ICML 2018 |
| Editors | Jennifer Dy, Andreas Krause |
| Publisher | International Machine Learning Society (IMLS) |
| Pages | 3376-3391 |
| Number of pages | 16 |
| ISBN (Electronic) | 9781510867963 |
| Publication status | Published - 1 Jan 2018 |
| Externally published | Yes |
| Event | 35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden Duration: 10 Jul 2018 → 15 Jul 2018 |
Publication series
| Name | 35th International Conference on Machine Learning, ICML 2018 |
|---|---|
| Volume | 5 |
Conference
| Conference | 35th International Conference on Machine Learning, ICML 2018 |
|---|---|
| Country | Sweden |
| City | Stockholm |
| Period | 10/07/18 → 15/07/18 |
Fingerprint
Cite this
}
Attention-based deep multiple instance learning. / Ilse, Maximilian; Tomczak, Jakub M.; Welling, Max.
35th International Conference on Machine Learning, ICML 2018. ed. / Jennifer Dy; Andreas Krause. International Machine Learning Society (IMLS), 2018. p. 3376-3391 (35th International Conference on Machine Learning, ICML 2018; Vol. 5).Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Attention-based deep multiple instance learning
AU - Ilse, Maximilian
AU - Tomczak, Jakub M.
AU - Welling, Max
PY - 2018/1/1
Y1 - 2018/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85057238355&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85057238355&partnerID=8YFLogxK
M3 - Conference contribution
T3 - 35th International Conference on Machine Learning, ICML 2018
SP - 3376
EP - 3391
BT - 35th International Conference on Machine Learning, ICML 2018
A2 - Dy, Jennifer
A2 - Krause, Andreas
PB - International Machine Learning Society (IMLS)
ER -