Issue No. 10 - Oct. (2012 vol. 34)
Daphna Weinshall , The Hebrew University of Jerusalem, Jerusalem
Alon Zweig , The Hebrew University of Jerusalem, Jerusalem
Hynek Hermansky , Brno University of Technology, Brno and Johns Hopkins University, Baltimore
Stefan Kombrink , Brno University of Technology, Brno
Frank W. Ohl , Leibniz Institute for Neurobiology, Magdeburg
Jörn Anemüller , Carl von Ossietzky University Oldenburg, Oldenburg
Jörg-Hendrik Bach , Carl von Ossietzky University Oldenburg, Oldenburg
Luc Van Gool , ETH, Zurich
Fabian Nater , ETH, Zurich
Tomas Pajdla , CTU, Prague
Michal Havlena , CTU, Prague
Misha Pavel , Oregon Health & Science University, Portland
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.
Data models, Training, Probabilistic logic, Electronic mail, Training data, Visualization, Vocabulary, out-of-vocabulary words., Novelty detection, categorization, object recognition
F. W. Ohl et al., "Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1886-1901, 2012.