Active Learning using Dirichlet Processes for Rare Class Discovery and Classification

Research output: Contribution to conferencePaperpeer-review

9 Citations (SciVal)
151 Downloads (Pure)


Real-world classification problems, such as visual surveillance and network intrusion detection, often contain common yet uninteresting background classes and rare but interesting classes, that need to be both discovered and classified. Active learning offers a suitable solution to joint rare class discovery and classification, by minimising the manual labelling of training data. A novel active learning approach is proposed, which automatically balances the competing goals of new class discovery and improving classification. Crucially it is free of tuneable parameters. Using Dirichlet processes a new active learning criterion is formulated, based on first computing the probability that unlabelled exemplars are from a new class, in addition to existing classes, and subsequently the probability of misclassification, which is then used for query selection. The proposed approach works with any probabilistic classification model and its effectiveness is demonstrated on multiple problems.
Original languageEnglish
Publication statusPublished - 2011
EventBritish Machine Vision Conference - University of Dundee, Dundee, UK United Kingdom
Duration: 29 Aug 20112 Sept 2011
Conference number: 22


ConferenceBritish Machine Vision Conference
Abbreviated titleBMVC
Country/TerritoryUK United Kingdom


Dive into the research topics of 'Active Learning using Dirichlet Processes for Rare Class Discovery and Classification'. Together they form a unique fingerprint.

Cite this