A Unifying Theory of Active Discovery and Learning

Timothy M. Hospedales, Shaogang Gong, Tao Xiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


For learning problems where human supervision is expensive, active query selection methods are often exploited to maximise the return of each supervision. Two problems where this has been successfully applied are active discovery – where the aim is to discover at least one instance of each rare class with few supervisions; and active learning – where the aim is to maximise a classifier’s performance with least supervision. Recently, there has been interest in optimising these tasks jointly, i.e., active learning with undiscovered classes, to support efficient interactive modelling of new domains. Mixtures of active discovery and learning and other schemes have been exploited, but perform poorly due to heuristic objectives. In this study, we show with systematic theoretical analysis how the previously disparate tasks of active discovery and learning can be cleanly unified into a single problem, and hence are able for the first time to develop a unified query algorithm to directly optimise this problem. The result is a model which consistently outperforms previous attempts at active learning in the presence of undiscovered classes, with no need to tune parameters for different datasets.
Original languageEnglish
Title of host publicationComputer Vision - ECCV 2012 - 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V
PublisherSpringer Berlin Heidelberg
Number of pages14
ISBN (Electronic)978-3-642-33715-4
ISBN (Print)978-3-642-33714-7
Publication statusPublished - 2012

Publication series

NameLecture Notes in Computer Science (LNCS)
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743


Dive into the research topics of 'A Unifying Theory of Active Discovery and Learning'. Together they form a unique fingerprint.

Cite this