Margarita Osadchy

My photo
Computer Science Department,
University of Haifa, Mount Carmel,
Haifa 31905, Israel
Office : +972-4-8288444
Fax : +972-4-8249331
Email : rita [at]cs [dot]haifa.ac.il

Research Interests:

My research interests are
  • Deep learning and machine learning
  • Data science
  • Privacy in biometric data
  • Security and privacy in machine learning
  • Computer Vision

Orginized Events

Current Courses:

Introduction to Machine Learning  203.4770
Deep Learning  203.3834

Past Courses:

Image and Video Recognition Seminar  203.3705
Methods in Biometric Recognition Seminar  203.3845
Introduction to Machine Learning  203.4770
Recognition and Classification in Images and Video Course 203.4780
Lab in Computer Vision  203.4720
Introduction to Computer Science  203.1110
Unsupervised Learning  203.4700

Selected Publications:

  • L. Heinrich, T. Golling, M. Kagan, S. Klein, M. Leigh, M. Osadchy, J.A. Raine, Masked particle modeling on sets: Towards self-supervised high energy physics foundation models, Machine Learning: Science and Technology, (2024)
  • Y. Wu, J. Liu, Y. Wang, S. J. Gibson, M. Osadchy, Y. Fang: Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers, IEEE Trans. Pattern Anal. Mach. Intell. 46(5): 3845-3861 (2024)
  • X. Niu, E. Li, J. Liu, Y. Wang, M. Osadchy, Y. Fang: Mind the Gap: Learning Modality-Agnostic Representations With a Cross-Modality UNet IEEE Trans. Image Process 33: 655-670 (2024)
  • A. Maalouf, G. Eini, B. Mussay, D. Feldman, M. Osadchy: A Unified Approach to Coreset Learning, IEEE Trans. Neural Networks Learn. Syst. 35(5): 6893-6905 (2024)
  • A. Poppe, J. Griffiths, S. Hu, J.J. Baumberg, M. Osadchy, S. Gibson, B de Nijs: Mapping Atomic-Scale Metal–Molecule Interactions: Salient Feature Extraction through Autoencoding of Vibrational Spectroscopy Data, The Journal of Physical Chemistry Letters 14 (34), 7603-7610 (2023)
  • D. Keren, M. Osadchy, A. Shahar: A Fast and Reliable Solution to PnP, Using Polynomial Homogeneity and a Theorem of Hilbert, Sensors 23(12): 5585 (2023)
  • M. Fintz, M. Osadchy, U. Hertz, Using deep learning to predict human decisions and using cognitive models to explain deep learning models, Scientific reports 12 (1), 4736 (2022)
  • B. Mussay, D. Feldman, S. Zhou, V. Braverman, M. Osadchy, Data-Independent Structured Pruning of Neural Networks via Coresets, IEEE Trans. Neural Networks Learn. Syst. 33(12): 7829-7841 (2022)
  • M. Osadchy, R. Kolodny, How deep learning tools can help protein engineers find good sequences, The Journal of Physical Chemistry B 125 (24), 6440-6450 (2021)
  • D. Keller, M. Osadchy, O. Dunkelman, Inverting Binarizations of Facial Templates Produced by Deep Learning (and Its Implications), IEEE Trans. Inf. Forensics Secur 16: 4184-4196 (2021)
  • F. Bai, J. Liu, X. Liu, M. Osadchy, C. Wang, S. J. Gibson, LSHR-Net: A hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network., Neurocomputing 406: 169-181 (2020)
  • B. Mussay, M. Osadchy, V. Braverman, S. Zhou, D. Feldman, Data-Independent Neural Pruning via Coresets., ICLR ,2020
  • M. Osadchy, O. Dunkelman, It is All in the System's Parameters: Privacy and Security Issues in Transforming Biometric Raw Data into Binary Strings, IEEE Transactions on Dependable and Secure Computing 2019.
  • R. Bernstein, M. Osadchy, D. Keren, A. Schuster, LDA classifier monitoring in distributed streaming systems, J. Parallel Distrib. Comput. 123: 156-167, 2019.
  • J. Liu S. J. Gibson, J. Mills, M. Osadchy, Dynamic spectrum matching with one-shot learning, Chemometrics and Intelligent Laboratory Systems, Vol. 184, pp. 175-181, 2019.
  • D. Raviv, T. Hazan, M. Osadchy, Hinge-Minimax Learner for the Ensemble of Hyperplanes, Journal of Machine Learning Research (JMLR) , 19(62):1?30, 2018.
  • G. Hadash, O. Sar-Shalom, M. Osadchy, Rank and rate: multi-task learning for recommender systems , Proceedings of the 12th ACM Conference on Recommender Systems, 2018.
  • J. Liu, S. J. Gibson, M. Osadchy, Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning, CoRR abs/1808.07270, 2018.
  • J. Liu, M. Osadchy, L, Ashton, M. Foster, C. J. Solomon, S. J. Gibson, Deep convolutional neural networks for Raman spectrum recognition: a unified solution, Analyst, vol. 142(21), pp. 4067-4074, 2017.
  • M. Ohana, O. Dunkelman, S. Gibson, M. Osadchy, HoneyFaces: Increasing the Security and Privacy of Authentication Using Synthetic Facial Images. CoRR abs/1611.03811 (2016), PDF.
  • M. Osadchy, J. Hernandez-Castro, S. Gibson, O. Dunkelman, D. Perez-Cabo, No Bot Expects the DeepCAPTCHA! Introducing Immutable Adversarial Examples with Applications to CAPTCHA Generation, IEEE Transactions on Information Forensics and Security, vol. 12, no. 11, 2017, pp. 2640 � 2653. PDF.
  • M. Osadchy, Y. Wang, O. Dunkelman, S.Gibson, J. Hernandez-Castro, and C. Solomon, GenFace: Improving Cyber Security using Realistic Synthetic Face Generation, International Symposium on Cyber Security, Cryptography and Machine Learning (CSCML), 2017.
  • M. Osadchy, D. Keren, D. Raviv, Recognition Using Hybrid Classifiers IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, No.4, 2016, pp. 759-771 [PDF ,Code]
  • M. Osadchy, T. Hazan, D. Keren, K-hyperplane Hinge-Minimax Classifier, Int. Confernce on Machine Leraning (ICML) 2015: 1558-1566.[PDF, Slides]
  • O. Dunkelman, M. Osadchy, M. Sharif, Secure authentication from facial attributes with no privacy loss, ACM Conference on Computer and Communications Security 2013, pp.1403-1406.
  • A. Netz and M. Osadchy, Recognition using Specular Highlights, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.35, No.3, 2013, pp.639-652. [project ].
  • M. Osadchy, D. Keren, and B. Fadida-Specktor, Hybrid Classifiers for Object Classification with a Rich Background, Proc. of European Conference on Computer Vision (ECCV) 2012, pp. 284-297, [PDF, Slides]
  • M. Osadchy, R. Kolodny, Maps of protein structure space reveal a fundamental relationship between protein structure and function, Proc. Natl. Acad. Sci., 2011,Vol. 108, No. 30. pp.12301-12306. [PDF,Suppl. Material]
  • A.Netz and M.Osadchy, Using Specular Highlights as Pose Invariant Features for 2D-3D Pose Estimation, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011 [PDF, project ]
  • B. Mosckovich, M. Osadchy, Illumination Invariant Representation for Privacy Preserving Face Identification, Workshop on Biometrics 2010, CVPRW 2010. Available files: [ project and code ]
  • M. Osadchy, B. Pinkas, A. Jarrous and B. Moskovich,SCiFI - A System for Secure Face Identification, 31st IEEE Symposium on Security & Privacy, May 16-19, 2010, Oakland, CA. (Received the best paper award!) [ PDF, project and code ]
  • M. Osadchy, E. Morash, Loose shape model for discriminative learning of object categories, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),2008, PDF.
  • M. Osadchy, D.W. Jacobs, R. Ramamoorthi, D. Tucker, Using Specularities in Comparing 3D Models and 2D Images, CVIU, Vol. 111(3), 2008, pp. 275-294. PDF
  • M. Osadchy, M. Lindenbaum, D.W. Jacobs, Surface Dependent Representations for Illumination Insensitive Image Comparison, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 29(1), 2007, pp. 98-111. PDF
  • M. Osadchy, Y. LeCun, M. Miller, Synergistic Face Detection and Pose Estimation with Energy-Based Models, Journal of Machine Learning Research, Volume 8, 2007, pp.1197 � 1215. PDF
  • M. Osadchy, D. Keren, Incorporating the Boltzmann Prior in Object Detection Using SVM, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2006, pp. 2095-2101, PDF
  • M. Osadchy, D.W. Jacobs, M. Lindenbaum, On the Equivalence of Common Approaches to Lighting Insensitive Recognition, Proc. IEEE International Conference on Computer Vision (ICCV) 2005.
  • M. Osadchy and D. Keren, Efficient Detection under Varying Illumination Conditions and Image Plane Rotations, Computer Vision and Image Understanding, Volume 93, Issue 3, March 2004, pp. 245-259.
  • M. Osadchy and D. Keren, A Rejection-Based Method for Event Detection in Video, IEEE Trans. on circuits and systems for video technology, Volume 14, Issue 4, April 2004, pp. 534-541.
  • M. Osadchy, M.L. Miller, Y. LeCun, Synergistic Face Detection and Pose Estimation with Energy Based Models, Advances in Neural Information Processing Systems (NIPS) 2004.
  • M. Osadchy, M. Lindenbaum and D.W. Jacobs, Whitening for photometric comparison of smooth surfaces, Proc. of European Conference on Computer Vision (ECCV), 2004.
  • M. Osadchy, M.L. Miller, Y. LeCun, Synergistic Face Detection and Pose Estimation, Machine Learning Workshop, Snowbird, 2004.
  • M. Osadchy, M. Lindenbaum and D.W. Jacobs, Whitening for photometric comparison of smooth surfaces, Int'l Workshop on Statistical and Computational Theories of Vision, 2003.
  • M. Osadchy, D.W. Jacobs and R. Ramamoorthi, Using specularities for recognition, IEEE International Conference on Computer Vision (ICCV), 2003, pp. 1512-1519.
  • M. Osadchy, D. Keren and Y. Gal, Anti-Sequences: Event detection by frame stacking, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2001, (II: 46-51).
  • M. Osadchy and D. Keren, Image Detection under varying illumination and pose, IEEE International Conference on Computer Vision (ICCV), 2001, (II: 668-673).
  • D. Keren M. Osadchy and C. Gotsman, Anti-Faces: A novel, fast method for image detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, No. 7, July 2001, pp. 747-761.
  • D. Keren, M.Osadchy and C. Gotsman, Anti-Faces for detection, Proc. of European Conference on Computer Vision (ECCV), June 2000.
  • D. Keren and M. Osadchy, Restoring subsampled color images, Machine Vision and Applications, Vol. 11, issue 4, 1999, pp.197-202.

Book Chapters:

  • Margarita Osadchy, Yann Le Cun, Matthew L. Miller, Synergistic Face Detection and Pose Estimation with Energy-Based Models , In Toward Category-Level Object Recognition, M. Hebert, C. Schmid, A. Zisserman (Eds.) Lecture Notes in Computer Science , Vol. 4170, 2007, pp 196-206.

Patents:

  • M. Osadchy, B. Pinkas, A. Jarrous, B. Moskovich, System for Secure Face Identification (SCiFI) and Methods Useful in Conjunction Therewith , US Patent App. 12/828,906, 2010.
  • M.L. Miller, M.Osadchy, and Y. LeCun, Synergistic face detection and pose estimation with energy-based models, US Patent No. 7236615, 2005.
  • M. Osadchy and D. Reisfeld, Method and apparatus for intracardially surveying conditions of a chamber of a heart, US patent No. 6385476,2002.
  • M. Osadchy and D. Reisfeld, Method and apparatus for mapping a chamber of a heart, US patent No. 6368285, 2002.