Attention-based Deep Multiple Instance Learning

Code

• github.com/AMLab-Amsterdam/AttentionDeepMIL
  OfficialIn paperpytorch★ 0
• github.com/ml-jku/hopfield-layers
  pytorch★ 1,907
• github.com/Xiyue-Wang/RetCCL
  pytorch★ 104
• github.com/ucla-starai/countloss
  pytorch★ 4
• github.com/swag2198/Intern-MeDAL_IITB
  pytorch★ 0
• github.com/Hazel-4/AttentionDeepMIL
  pytorch★ 0
• github.com/KostiukIvan/Multiple-instance-learning-with-graph-neural-networks
  pytorch★ 0
• github.com/DhruvilKarani/mil_mnist
  pytorch★ 0
• github.com/ThomasHenckel/Attention_Deep_MIML
  tf★ 0
• github.com/srinath-niz/google_youtube8m_2019
  tf★ 0

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.

Tasks

Reproductions