Beyond novelty detection: Incongruent events, when general and specific classifiers disagree

Daphna Weinshall*, Alon Zweig, Hynek Hermansky, Stefan Kombrink, Frank W. Ohl, Jörn Anemüller, Jörg Hendrik Bach, Luc Van Gool, Fabian Nater, Tomas Pajdla, Michal Havlena, Misha Pavel

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

19 Scopus citations


Unexpected stimuli are a challenge to any machine learning algorithm. Here, we identify distinct types of unexpected events when general-level and specific-level classifiers give conflicting predictions. We define a formal framework for the representation and processing of incongruent events: Starting from the notion of label hierarchy, we show how partial order on labels can be deduced from such hierarchies. For each event, we compute its probability in different ways, based on adjacent levels in the label hierarchy. An incongruent event is an event where the probability computed based on some more specific level is much smaller than the probability computed based on some more general level, leading to conflicting predictions. Algorithms are derived to detect incongruent events from different types of hierarchies, different applications, and a variety of data types. We present promising results for the detection of novel visual and audio objects, and new patterns of motion in video. We also discuss the detection of Out-Of-Vocabulary words in speech recognition, and the detection of incongruent events in a multimodal audiovisual scenario.

Original languageAmerican English
Article number6122029
Pages (from-to)1886-1901
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number10
StatePublished - 2012

Bibliographical note

Funding Information:
This study was supported by the European Union under the DIRAC integrated project IST-027787.


  • Novelty detection
  • categorization
  • object recognition
  • out-of-vocabulary words


Dive into the research topics of 'Beyond novelty detection: Incongruent events, when general and specific classifiers disagree'. Together they form a unique fingerprint.

Cite this