Learning with Constrained and Unlabelled Data

Authors:
Tilman Lange;Martin H. C. Law;Anil K. Jain;Joachim M. Buhmann
Affiliations:
ETH Zurich;Michigan State University;Michigan State University;ETH Zurich
Venue:
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 17

A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Penalized Probabilistic Clustering

Neural Computation
Revisiting probabilistic models for clustering with pair-wise constraints

Proceedings of the 24th international conference on Machine learning
BoostCluster: boosting clustering by pairwise constraints

Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Constrained Clustering Via Concavity Cuts

CPAIOR '07 Proceedings of the 4th international conference on Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems
Semi-supervised graph clustering: a kernel approach

Machine Learning
A global optimization method for semi-supervised clustering

Data Mining and Knowledge Discovery
Using hidden Markov random fields to combine distributional and pattern-based word clustering

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Metric learning for semi-supervised clustering using pairwise constraints and the geometrical structure of data

Intelligent Data Analysis
Data clustering: 50 years beyond K-means

Pattern Recognition Letters
Non-linear metric learning using pairwise similarity and dissimilarity constraints and the geometrical structure of data

Pattern Recognition
Semi-supervised approach for finding cancer sub-classes on gene expression data

BSB'10 Proceedings of the Advances in bioinformatics and computational biology, and 5th Brazilian conference on Bioinformatics
A new semi-supervised clustering algorithm with pairwise constraints by competitive agglomeration

Applied Soft Computing
Data clustering: a user’s dilemma

PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence
An experimental study of constrained clustering effectiveness in presence of erroneous constraints

Information Processing and Management: an International Journal
Semi-supervised change detection using modified self-organizing feature map neural network

Applied Soft Computing
Semi-supervised projected model-based clustering

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification problems abundantly arise in many computer vision tasks 驴 being of supervised, semi-supervised or unsupervised nature. Even when class labels are not available, a user still might favor certain grouping solutions over others. This bias can be expressed either by providing a clustering criterion or cost function and, in addition to that, by specifying pairwise constraints on the assignment of objects to classes. In this work, we discuss a unifying formulation for labelled and unlabelled data that can incorporate constrained data for model fitting. Our approach models the constraint information by the maximum entropy principle. This modeling strategy allows us (i) to handle constraint violations and soft constraints, and, at the same time, (ii) to speed up the optimization process. Experimental results on face classification and image segmentation indicates that the proposed algorithm is computationallyefficient and generates superior groupings when compared with alternative techniques.