Timezone: »

Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree
Daphna Weinshall · Hynek Hermansky · Alon Zweig · Jie Luo · Holly B Jimison · Frank W Ohl · Misha Pavel

Unexpected stimuli are a challenge to any machine learning algorithm. Here we identify distinct types of unexpected events, focusing on 'incongruent 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 (according to the partial order) in the label hierarchy . An incongruent event is an event where the probability computed based on some more specific level (in accordance with the partial order) is much smaller than the probability computed based on some more general level, leading to conflicting predictions. We derive algorithms to detect incongruent events from different types of hierarchies, corresponding to class membership or part membership. Respectively, we show promising results with real data on two specific problems: Out Of Vocabulary words in speech recognition, and the identification of a new sub-class (e.g., the face of a new individual) in audio-visual facial object recognition.

Author Information

Daphna Weinshall (Hebrew Univeristy of Jerusalem)
Hynek Hermansky
Alon Zweig (Hebrew University)
Roger Luo (Snap Inc.)
Holly B Jimison (Oregon Health & Science University)
Frank W Ohl (Leibniz Institute for Neurobiology)
Misha Pavel (OHSU)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors