Adrian Barbu

   Associate Professor, Department of Statistics, Florida State University.
  
   Research interests:
       - Computer Vision
       - Machine Learning
       - Learning Based Optimization
       - Medical Imaging

Research:

1. Two-round EM - Theoretical guarantees for an EM algorithm for estimating mixtures of binary templates corrupted by Bernoulli noise.
2. Artificial Prediction Markets - A novel online learning method inspired from economics that learns a probability function that
   minimizes the KL divergence to the true distribution given by the training examples.
3. Active Random Fields - A MRF based model trained together with a fast and suboptimal inference algorithm achieves
   thousands of times speedup without loss in accuracy.
4. Marginal Space Learning - A learning-based optimization method that achieves many orders of magnitude speedup for
   object detection in large parameter spaces.
5. Graph Partition by Swendsen-Wang Cuts - a stochastic graph partition algorithm. It performs fast inference in the graph partition
   space, guided by a probability model and uses low level cues to speed up convergence. The algorithm is ergodic and reversible. 

Representative Publications

1. A. Barbu, M. Pavlovskaia, S.C. Zhu. Rates for Inductive Learning of Compositional Models. AAAI Workshop Replearn 2013 (pdf)
2. A. Barbu, Y. N. Wu, S.C. Zhu. Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee.(arxiv)
3. N. Lay, A. Barbu. The Artificial Regression Market. (arxiv)
4. A. Barbu. Multi-Path Marginal Space Learning for Object Detection. Submitted. (pdf)
5. A. Barbu. Hierarchical Object Parsing from Structured Noisy Point Clouds. IEEE PAMI, 35, No. 7, 1649–1659, 2013. (pdf, arxiv, slides)
6. L. Ding, A. Barbu, A. Meyer-Baese. Learning a Quality-Based Ranking for Feature Point Trajectories. ACCV 2012 (pdf)
7. L. Ding, A. Barbu, A. Meyer-Baese. Motion Segmentation by Velocity Clustering with Estimation of Subspace Dimension. ACCV Workshop DTCE 2012 (pdf)
8. A. Barbu, N. Lay. An Introduction to Artificial Prediction Markets for Classification. Journal of Machine Learning Research, 13, 2177–2204, 2012. (pdf)
9. A. Barbu, M. Suehling, X. Xu, D. Liu, S. K. Zhou, D. Comaniciu. Automatic Detection and Segmentation of Lymph Nodes from CT Data. IEEE Trans Medical Imaging, 31, No. 2, 240–250, 2012.(pdf)
10. W. Wu, T. Chen , A. Barbu, P. Wang, N. Strobel, S. Zhou, D. Comaniciu. Learning-based Hypothesis Fusion for Robust Catheter Tracking in 2D X-ray Fluoroscopy. CVPR 2011 (pdf)
11. F. Bunea, A. Tsybakov, M. Wegkamp and A.Barbu. SPADES and mixture models. Annals of Statistics 38, No. 4, 2525–2558, 2010.(pdf)
12. F. Bunea and A.Barbu. Dimension reduction and variable selection in case control studies via regularized likelihood optimization. Electronic Journal of Statistics, 3, 2009. (pdf)
13. A. Barbu. Training an Active Random Field for Real-Time Image Denoising. IEEE Trans. Image Processing, 18, November 2009. (pdf, ppt)
14. S. Seifert, A. Barbu, S. Zhou, D. Liu, J. Feulner, M. Huber, M. Suehling, A. Cavallaro, D. Comaniciu. Hierarchical parsing and semantic navigation of full body CT data. SPIE Medical Imaging, 2009 (pdf)
15. Y. Zheng, A. Barbu, B. Georgescu, M. Scheuering and D. Comaniciu. Four-Chamber Heart Modeling and Automatic Segmentation
    for 3D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features. IEEE Trans Medical Imaging, November 2008. (pdf)
16. L. Lu, A. Barbu, M. Wolf, J. Liang, M. Salganicoff, D. Comaniciu. Accurate Polyp Segmentation for 3D CT Colonography Using Multi-Staged Probabilistic Binary Learning and Compositional Model. CVPR 2008.(pdf)
17. A. Barbu, V. Athitsos, B. Georgescu, S. Boehm, P. Durlak, D. Comaniciu. Hierarchical Learning of Curves: Application to Guidewire Localization in Fluoroscopy. CVPR 2007 (pdf)
18. A. Barbu, S.C. Zhu. Generalizing Swendsen-Wang for Image Analysis. J. Comp. Graph. Stat. 16, No 4, 2007 (pdf)
19. A. Barbu, S.C. Zhu. Generalizing Swendsen-Wang to sampling arbitrary posterior probabilities, PAMI, 27, August 2005 (pdf)
20. A. Barbu, S.C. Zhu. Multigrid and Multi-level Swendsen-Wang Cuts for Hierarchic Graph Partition, CVPR 2004 (pdf)

Awards:

1. 2011 Thomas A. Edison Patent Award. System and Method for Segmenting Chambers of a Heart in a Three Dimensional Image. Patent No. 7,916,919. video

Funding:

1. SEE on a Unified Foundation for Representation, Inference and Learning, DARPA, 231k (PI on subcontract from UCLA)
2. MCS: Research on Detection and Classification of 2D and 3D Shapes in Cluttered Point Clouds. NSF, 400k (CO-PI)
3. Statistical and Semantic Approaches for Object, Activity and Intent Recognition. ONR, 443k (CO-PI)
4. Landmark Detection Using Discriminative Anatomical Network And Active Random Fields. Siemens, 31k (PI)
5. Cooperative Systems: Task Allocation for Heterogeneous Agent Teams Via Stochastic Clustering Auctions. ARO, 16k (subcontract)

Invited Talks

1. The Artificial Prediction Market, ICML Workshop on Markets, Mechanisms and Multi-Agent Models, Edinburgh, July 1st, 2012 (pdf)
2. Hierarchical Object Parsing from Noisy Point Clouds, Siemens Corporate Research, August 16th, 2011
3. Artificial Prediction Markets for Classification, Regression and Density Estimation, UCLA, August 11th, 2011
4. Automatic Detection and Segmentation of Lymph Nodes. NIH, December 8th 2010
5. Supervised Aggregation of Classifiers using Artificial Prediction Markets, SRCOS 2010 (pdf)
6. Supervised Aggregation using Artificial Prediction Markets. UCLA, November 10th, 2009
7. Marginal Space Learning for Fast Object Detection in Medical Imaging. Tutorial on Discriminative Learning Methods in Medical Imaging, MICCAI 2009
8. Training an Active Random Field for Real-Time Image Denoising. Max Plank Institute, Saarbrucken, Germany, July 16th, 2008
9. The Swendsen-Wang Cuts Algorithm with Applications in Computer Vision, Georgia Tech University, June 2008
10. Active Random Fields for Real-Time Image Denoising, Siemens Corporate Research, May 2008
11. Hierarchical Image-Motion Segmentation using Swendsen-Wang Cuts, Third Cape Cod MCMC Workshop , Harvard, 2007 (ppt)
12. A General Clustering Sampling Method for Bayesian Inference, Joint Statistical Meetings, Minneapolis, August 10, 2005
13. Swendsen-Wang for Perceptual Grouping. Second Cape Cod Workshop on Monte Carlo Methods, 2004

Patents:

1. A. Barbu, W. Zhang, N. Strobel, A. Galant, U. Bill, D. Comaniciu. Method and system for catheter detection and tracking in a fluoroscopic image sequence. Patent no 8,396,533
2. A. Barbu, M. Suehling, X. Xu, D. Liu, S.K. Zhou, D. Comaniciu. Method and System for Automatic Detection and Segmentation of Axillary Lymph Nodes. Patent no 8,391,579
3. 1. W. Zhang, Y. Zhu, A. Barbu, R. Socher, S. Boehm, P. Durlak, D. Comaniciu. Methods and Apparatus for Virtual Coronary Mapping. Patent 8,355,550
4. L. Lu, A. Barbu, M. Wolf, S. Lakare, L. Bogoni, M. Salganicoff, D. Comaniciu. Method and System for Polyp Segmentation for 3D Computed Tomography Colonography. Patent 8,184,888
5. L. Lu, A. Barbu, M. Wolf, S. Lakare, L. Bogoni, M. Salganicoff, D. Comaniciu. User Interface for Polyp Annotation, Segmentation and Measurement in 3D Computed Tomography Colonography. Patent 8,126,244
6. R. Socher, A. Barbu, B. Georgescu, W. Zhang, P. Durlak, S. Bohm, D. Comaniciu. Method and system for vessel segmentation in fluoroscopic images. Patent 8,121,367
7. Y. Zhu, W. Zhang, A. Barbu, S. Prummer, M. Ostermeier, C. Reddy, D. Comaniciu. System and Method for Coronary Digital Subtraction Angiography. Patent 8,094,903
8. W. Zhang, A. Barbu, S. Prummer, M. Ostermeier and D. Comaniciu. Method and System for Evaluating Image Segmentation Based on Visibility. Patent 8,086,006
9. A. Barbu, L. Lu, L. Bogoni, M. Salganicoff, D. Comaniciu. Method and System for Detection and Registration of 3D Objects Using Incremental Parameter Learning. Patent 8,068,654
10. A. Barbu, V. Athitsos, B. Georgescu, P. Durlak, D. Comaniciu. System and Method for Online Optimization of Guidewire Visibility in Fluoroscopic Systems. Patent 8,050,482
11. A. Barbu, Y. Zheng, Y. Zhing, B. Georgescu, D. Comaniciu. System and Method for Detecting an Object in a High Dimensional Space. Patent 8,009,900
12. B. Georgescu, P. Durlak, V. Athitsos, A. Barbu, D. Comaniciu. System and Method for Simultaneously Subsampling Fluoroscopic Images and Enhancing Guidewire Visibility. Patent 7,970,191
13. W. Zhang, A. Barbu, S. Prummer, M. Ostermeier, C. Reddy, D. Comaniciu. System and Method for Coronary Digital Subtraction Angiography. Patent 7,940,971
14. Y. Zheng, A. Barbu, B. Georgescu, M. Scheuering, D. Comaniciu. System and Method for Segmenting Chambers of a Heart in a Three Dimensional Image. Patent 7,916,919
15. S.K. Zhou, J. Shao, J. Dowdall, A. Barbu, B. Georgescu, D. Comaniciu. System and Method for Using a Similarity Function to Perform Appearance Matching in Image Pairs. Patent 7,831,074
16. A. Barbu, V. Athitsos, B. Georgescu, P. Durlak, S. Boehm, D. Comaniciu. System and Method for Detecting and Tracking a Guidewire In A Fluoroscopic Image Sequence. Patent 7,792,342
17. A. Barbu, L. Lu, M. Wolf, L. Bogoni, M. Salganicoff. Interface Utilisateur pour une Annotation, une Segmentation et une Mesure de Polype en Colonoscopie Virtuelle 3D. Europe Patent WO/2009/042034
18. A. Barbu, L. Bogoni, D. Comaniciu. System and Method For Detecting A Three Dimensional Flexible Tube In An Object. Patent 7,783,097
19. Z. Tu, A. Barbu. Probabilistic Boosting Tree Framework for Learning Discriminative Models. Patent 7,702,596
20. Z. Tu, X. Zhou, D. Comaniciu, L. Bogoni, A. Barbu. System and Method for Using Learned Discriminative Models to Segment Three dimensional Colon Image Data. Patent 7,583,831
21. Z. Tu, A. Barbu, D. Comaniciu. Method for Detecting Polyps in a Three Dimensional Image Volume. Patent 7,558,413

Teaching:

• Applied Machine Learning - STA 4634/5635 (syllabus) Spring 08,09,11,13
• Introduction to Applied Statistics - STA 5126 (syllabus) Fall 2012
• Applied Linear Regression - STA 4203/5207 (syllabus) Fall 2007-2012
• Medical Image Analysis, (syllabus) Spring 10,12

Education: