The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.10 - Oct. (2012 vol.34)
pp: 1886-1901
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
ABSTRACT
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.
INDEX TERMS
Data models, Training, Probabilistic logic, Electronic mail, Training data, Visualization, Vocabulary, out-of-vocabulary words., Novelty detection, categorization, object recognition
CITATION
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, "Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 10, pp. 1886-1901, Oct. 2012, doi:10.1109/TPAMI.2011.279
REFERENCES
[1] M. Markou and S. Singh, "Novelty Detection: A Review-Part 1: Statistical Approaches," Signal Processing, vol. 83, no. 12, pp. 2499-2521, 2003.
[2] M. Markou and S. Singh, "Novelty Detection: A Review-Part 2: Neural Network Based Approaches," Signal Processing, vol. 83, no. 12, pp. 2481-2497, 2003.
[3] D. Tax and R. Duin, "Support Vector Data Description," Machine Learning, vol. 54, no. 1, pp. 45-66, 2004.
[4] B. Scholkopf, R. Williamson, A. Smola, J. Shawe-Taylor, and J. Platt, "Support Vector Method for Novelty Detection," Proc. Advances in Neural Information Processing Systems, 2000.
[5] D. Yeung and C. Chow, "Parzen-Window Network Intrusion Detectors," Proc. Int'l Conf. Pattern Recognition, 2002.
[6] C.P. Diehl and J.B. HampshireII, "Real-Time Object Classification and Novelty Detection for Collaborative Video Surveillance," Proc. IEEE Int'l Joint Conf. Neural Networks, 2002.
[7] S. Chopra, R. Hadsell, and Y. LeCun, "Learning a Similarity Metric Discriminatively, with Application to Face Verification," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
[8] G.S. Berns, J.D. Cohen, and M.A. Mintun, "Brain Regions Responsive to Novelty in the Absence of Awareness," Science, vol. 276, no. 5316, pp. 1272-1275, 1997.
[9] B. Rokers, E. Mercado, M.T. Allen, C.E. Myers, and M.A. Gluck, "A Connectionist Model of Septohippocampal Dynamics during Conditioning: Closing the Loop," Behavioral Neuroscience, vol. 116, no. 1, pp. 48-62, 2002.
[10] M. Marszałek and C. Schmid, "Constructing Category Hierarchies for Visual Recognition," Proc. 10th European Conf. Computer Vision, 2008.
[11] J. Sivic, B.C. Russell, A. Zisserman, W.T. Freeman, and A.A. Efros, "Unsupervised Discovery of Visual Object Class Hierarchies," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[12] A. Bar-Hillel and D. Weinshall, "Subordinate Class Recognition Using Relational Object Models," Proc. Advances in Neural Information Processing Systems, vol. 19, 2006.
[13] A. Zweig and D. Weinshall, "Exploiting Object Hierarchy: Combining Models from Different Category Levels," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[14] M. Marszałek and C. Schmid, "Semantic Hierarchies for Visual Object Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[15] A. Bar-Hillel, T. Hertz, and D. Weinshall, "Efficient Learning of Relational Object Class Models," Proc. IEEE Int'l Conf. Computer Vision, 2005.
[16] B. Leibe, A. Leonardis, and B. Schiele, "Robust Object Detection with Interleaved Categorization and Segmentation," Int'l J. Computer Vision, vol. 77, no. 1, pp. 259-289, 2008.
[17] R. Fergus, P. Perona, and A. Zisserman, "Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition," Int'l J. Computer Vision, vol. 71, no. 3, pp. 273-303, 2007.
[18] J. Matas et al., "Comparison of Face Verification Results on the XM2VTS Database," Proc. Int'l Conf. Pattern Recognition, 2000.
[19] G. Griffin, A. Holub, and P. Perona, "Caltech-256 Object Category Dataset," Technical Report UCB/CSD-04-1366, California Inst. of Technology, http://www.vision.caltech.edu/Image_DataSets Caltech256, 2007.
[20] J.S. Garofolo, L.F. Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, N.L. Dahlgren, and V. Zue, "Timit Acoustic-Phonetic Continuous Speech Corpus," Linguistic Data Consortium, Philadelphia, 1993.
[21] H. Hermansky and N. Morgan, "Rasta Processing of Speech," IEEE Trans. Speech and Audio Processing, vol. 2, no. 4, pp. 578-589, Oct. 1994.
[22] J.-H. Bach and J. Anemüller, "Detecting Novel Objects in Acoustic Scenes through Classifier Incongruence," Proc. Int'l Conf. Spoken Language Processing, 2010.
[23] J. Anemüller, D. Schmidt, and J.-H. Bach, "Detection of Speech Embedded in Real Acoustic Background Based on Amplitude Modulation Spectrogram Features," Proc. Int'l Conf. Spoken Language Processing, 2008.
[24] T. Pajdla, L. Van Gool, M. Havlena, J. Heller, A. Torii, A. Ess, J.-H. Bach, H. Kayser, J. Anemüller, and P. Van Hengel, "Incongruence Detection in Audio-Visual Processing," Research Report CTU-CMP-2008-28, Center for Machine Perception, K13133 FEE Czech Technical Univ., Prague, Czech Republic, Dec. 2008.
[25] H. Ketabdar, M. Hannemann, and H. Hermansky, "Detection of Out-of-Vocabulary Words in Posterior Based ASR," Proc. European Conf. Speech Comm. and Technology, 2007.
[26] L. Burget, P. Schwarz, P. Matějka, M. Hannemann, A. Rastrow, C. White, S. Khudanpur, H. Hermansky, and J. Černocký, "Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs," Proc. 33rd IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, pp. 4081-84, 2008.
[27] S. Kombrink, L. Burget, P. Matějka, M. Karafiát, and H. Hermansky, "Posterior-Based Out of Vocabulary Word Detection in Telephone Speech," Proc. Int'l Conf. Spoken Language Processing, pp. 80-83, 2009.
[28] G.R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface," Intel Technology J., vol. 2, no. Q2, pp. 12-21, 1998.
[29] P. Felzenszwalb, D. Mcallester, and D. Ramanan, "A Discriminatively Trained Multiscale, Deformable Part Model," Proc. IEEE Conf. Computer Vision and Pattern Recognitio, 2008.
[30] F. Nater, H. Grabner, T. Jaeggli, and L. Van Gool, "Tracker Trees for Unusual Event Detection," Proc. IEEE Int'l Conf. Computer Vision Workshop Visual Surveillance, 2009.
[31] C.M. Bishop, Pattern Recognition and Machine Learning. Springer, 2007.
[32] N. Ulanovsky, L. Las, D. Farkas, and I. Nelken, "Multiple Time Scales of Adaptation in Auditory Cortex Neurons," The J. Neuroscience, vol. 24, pp. 10440-10453, 2004.
[33] F.W. Ohl and H. Scheich, "Orderly Cortical Representation of Vowels Based on Formant Interaction," Proc. Nat'l Academy of Sciences, vol. 94, pp. 9440-9444, 1997.
[34] G.E. Peterson and H.L. Barney, "Control Methods Used in a Study of the Vowels," J. Acoustical Soc. Am., vol. 24, pp. 175-184, 1952.
[35] F.W. Ohl and H. Scheich, "Change in Pattern of Ongoing Cortical Activity with Auditory Category Learning," Nature, vol. 412, pp. 733-736, 2001.
[36] M. Deliano, H. Scheich, and F.W. Ohl, "Auditory Cortical Activity after Intracortical Microstimulation and Its Role for Sensory Processing and Learning," The J. Neuroscience, vol. 29, pp. 15898-15909, 2009.
51 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool