Multi-Instance Multi-Label Learning with Application to Scene Classification

The MIT Press eBooksPublished 7 September 2007

Zhi‐Hua Zhou, Min-Ling Zhang

DOI10.7551/mitpress/7503.003.0206

Citations474

TL;DR

This paper formalizes multi-instance multi-label learning, where each training example is associated with not only multiple instances but also multiple class labels, and proposes the MIMLBOOST and MIMLSVM algorithms which achieve good performance in an application to scene classification.

Abstract

In this paper, we formalize multi-instance multi-label learning, where each training example is associated with not only multiple instances but also multiple class labels. Such a problem can occur in many real-world tasks, e.g. an image usually contains multiple patches each of which can be described by a feature vector, and the image can belong to multiple categories since its semantics can be recognized in different ways. We analyze the relationship between multi-instance multi-label learning and the learning frameworks of traditional supervised learning, multiinstance learning and multi-label learning. Then, we propose the MIMLBOOST and MIMLSVM algorithms which achieve good performance in an application to scene classification. 1

Keywords

Computer Science

ACM Transactions on Intelligent Systems and TechnologyLIBSVM

41,340 Citations2011Chih-Chung Chang, Chih‐Jen Lin

Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.

Artificial IntelligenceSolving the multiple instance problem with axis-parallel rectangles

2,886 Citations1997Thomas G. Dietterich, Richard H. Lathrop +1 more

Three kinds of algorithms that learn axis-parallel rectangles to solve the multiple instance problem are described and compared, giving 89% correct predictions on a musk odor prediction task.

Pattern RecognitionLearning multi-label scene classification

2,255 Citations2004Matthew Boutell, Jiebo Luo +2 more

A framework to handle semantic scene classification, where a natural scene may contain multiple objects such that the scene can be described by multiple class labels, is presented and appears to generalize to other classification problems of the same nature.

Machine LearningBoosTexter: A Boosting-based System for Text Categorization

2,194 Citations2000Robert E. Schapire, Yoram Singer

This work describes in detail an implementation, called BoosTexter, of the new boosting algorithms for text categorization tasks, and presents results comparing the performance of Boos Texter and a number of other text-categorization algorithms on a variety of tasks.

View PDF

Choice Reviews OnlineMeasure, topology, and fractal geometry

650 Citations1991

Journal of Machine Learning ResearchImage Categorization by Learning and Reasoning with Regions

633 Citations2004Yixin Chen, James Z. Wang

This paper presents a new learning technique, which extends Multiple-Instance Learning (MIL), and its application to the problem of region-based image categorization, and provides experimental results on an image categorizing problem and a drug activity prediction problem.

Multiple-Instance Learning for Natural Scene Classification

569 Citations1998Oded Maron, Aparna Lakshmi Ratan

It is shown that very simple templates are suu-cient, and that performance improves with more user interaction, and the Diverse Density algorithm which is a method of learning from ambiguous examples is discussed.

Learning with Multiple Labels

295 Citations2002Rong Jin, Zoubin Ghahramani

This paper proposes a novel discriminative approach for handling the ambiguity of class labels in the training examples and shows that the approach is able to find the correct label among the set of candidate labels and actually achieve performance close to the case when each training instance is given a single correct label.

Lecture notes in computer scienceLogistic Regression and Boosting for Labeled Bags of Instances

222 Citations2004Xin Xu, Eibe Frank

This paper upgrades linear logistic regression and boosting to multi-instance data, where each example consists of a labeled bag of instances, and presents empirical results for artificial data generated according to the underlying generative model that is assumed.

Knowledge and Information SystemsSolving multi-instance problems with classifier ensemble based on constructive clustering

149 Citations2006Zhi‐Hua Zhou, Min-Ling Zhang

This paper proposes a new solution which goes at an opposite way, that is, adapting the multi-instance representation to single-instance learning algorithms, and works well on standard as well as generalized multi-instance problems.