Multiple instance learning: A survey of problem characteristics and applications

By Marc-Andre Carbonneau, Veronika Cheplygina, Eric Granger, Ghyslain Gagnon. Pattern Recognition, 2016

750 citations recorded by the source corpus.

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research. Code is available on-line at https://github.com/macarbonneau/MILSurvey.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1ba54fdb71e4f77447460616908f1b931e61c251

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Transformers in Medical Image Analysis: A Review (2022, background): “Although many existing MIL methods assume that positive and negative instances are sampled independently from a positive and a negative distribution [154], instances in a bag are relational, especially in medical image analysis.”
Hopfield Networks is All You Need (2020, background): “With over 30 billion sequences in total, this represents one of the largest multiple instance learning experiments ever conducted [15] (for details see [70], appendix, Section A2).”
Using Neural Network Formalism to Solve Multiple-Instance Problems (2016, background): “The Interested reader is referred to [1,12,4] for a more thorough discussion of a problem and algorithms.”
Modern Hopfield Networks and Attention for Immune Repertoire Classification (2020, background): “However, in MIL problems considered by machine learning methods up to now, the number of instances per bag is in the range of hundreds or few thousands (Carbonneau et al., 2018; Lee et al., 2019) (see also Tab.”
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection (2019, background): “…that the label Y = 0 is noiseless, since it means all snippets v i in the video V are normal: However, Y = 1 is noisy because in this case the video V is partially made up of anomalous clips: This is referred to as one-sided label noise [7, 9, 55], for the noise only appears along with Y = 1 .”
Federated learning for medical image analysis: A survey (2023, methodology): “Multiple-instance learning (Quellec et al., 2017; Carbonneau et al., 2018) is a representative method to handle this problem.”
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning (2020, background): “We refer the readers to [4] for a survey.”