Multiple instance classification: Review, taxonomy and comparative study

By Jaume Amores. 2013

623 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Plant Science

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Plant Science

Citations in the corpus

Learning Theory for Distribution Regression (2014, methodology): “The MIL approach has been applied in several domains; see the reviews from Babenko (2004); Zhou (2004); Foulds and Frank (2010); Amores (2013).”
Revisiting multiple instance neural networks (2016, methodology): “These methods belong to the category of embedded-space MIL algorithms defined in the survey [2].”
Clustering for point pattern data (2017, background): “In multiple instance learning [22], [23], the ‘bags’ are indeed point patterns.”
Model-Based Multiple Instance Learning (2017, background): “The emerging area of machine learning dedicated to point pattern data is commonly known as Multiple Instance (MI) learning [1], [2].”
Using Neural Network Formalism to Solve Multiple-Instance Problems (2016, background): “Later works (see reviews [1,11]) have introduced different assumptions on relationships between the labels on the instance level and labels of bags or even dropped the notion of instance-level labels and considered only labels on the level of bags, i.”
Computer vision for high content screening (2016, methodology): “Xu et al. (2014) used a combination of features extracted from convolutional networks and multiple instance learning (Amores, 2013) to classify patches from histopathology images as containing colon cancer or not.”
Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis (2020, methodology): “This procedure shares the similar idea of “vocabulary-based paradigm” [41] in”
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time (2017, methodology): “We refer the reader to Amores (2013); Herrera et al. (2016) for an in-depth study of MIL. In this section we apply the previously developed ideas to MIL and give the first provable learning results for concrete schemes that do not rely on unproven assumptions. Comparison to Previous Work. Under the ”
Group-Based Active Learning of Classification Models (2017, methodology): “MIAL follows the basic assumptions of Multiple Instance Learning framework (Amores 2013): a bag is a meaningful unity of instances, bag labels are asymmetric, and the goal is to train a bag-level classifier.”
Model-based classification and novelty detection for point pattern data (2016, methodology): “According to the recent review article [9], there are three paradigms for multiple instance classification, namely Instance-Space (IS), EmbeddedSpace (EM), and Bag-Space (BS).”
Multi-Instance Learning With Emerging Novel Class (2021, methodology): “Since then, many effective multi-instance learning algorithms have been developed in the literature [3], [39], [40], [41], to name a few: EM-DD, miSVM, MIBoosting, MILES, miGraph, miFV, etc.”
A brief introduction to weakly supervised learning (2018, background): “There is also a categorization [2] which groups the algorithms into instance-space paradigm where the instance-level responses are aggregated, bagspace paradigm where the bags are treated as a whole, and embedded-space paradigm where learning is performed in an embedded feature space.”
DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification (2022, background): “A large proportion of existing weakly supervised works for WSI classification are characterized as “multiple instance learning” (MIL) [1, 5, 8, 25].”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “[2014] lesion segmentation self-training, active An et al. [2016] AD classification graph-based Baur et al. [2017] MS lesion segmentation graph-based Moradi et al.”