University of Surrey

Test tubes in the lab Research in the ATI Dance Research

On detection of novel categories and subcategories of images using incongruence

Coppi, D, De Campos, T, Yan, F, Kittler, J and Cucchiara, R (2014) On detection of novel categories and subcategories of images using incongruence

Full text not available from this repository.


Novelty detection is a crucial task in the development of autonomous vision systems. It aims at detecting if samples do not conform with the learnt models. In this paper, we consider the problem of detecting novelty in object recognition problems in which the set of object classes are grouped to form a semantic hierarchy. We follow the idea that, within a semantic hierarchy, novel samples can be defined as samples whose categorization at a specific level contrasts with the categorization at a more general level. This measure indicates if a sample is novel and, in that case, if it is likely to belong to a novel broad category or to a novel sub-category. We present an evaluation of this approach on two hierarchical subsets of the Caltech256 objects dataset and on the SUN scenes dataset, with different classification schemes. We obtain an improvement over Weinshall et al. and show that it is possible to bypass their normalisation heuristic. We demonstrate that this approach achieves good novelty detection rates as far as the conceptual taxonomy is congruent with the visual hierarchy, but tends to fail if this assumption is not satisfied. Copyright 2014 ACM.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions : Surrey research (other units)
Authors :
Coppi, D
De Campos,
Cucchiara, R
Date : 1 January 2014
DOI : 10.1145/2578726.2578769
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:16
Last Modified : 23 Jan 2020 18:26

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800