Organizing Committee
Abstract

Optimization appears in many computer vision and image processing problems such as image restoration (denoising, inpainting, compressed sensing), multi-view reconstruction, shape from X, object detection, image segmentation, optical flow, matching, and network training. While there are formulations allowing for global optimal optimization, e.g. using convex objectives or exact combinatorial algorithms, many problems in computer vision and image processing require efficient approximation methods.

Optimization methods that are widely used range from graph-based techniques and convex relaxations to greedy approaches (e.g. gradient descent). Each method has different efficiency and optimality guarantees. The goal of this workshop is a broad discussion of mathematical models (objectives and constraints) and robust efficient optimization methods (exact or approximate, discrete or continuous) addressing existing issues and advancing the state of the art.

Confirmed Speakers & Participants

  • Speaker
  • Poster Presenter
  • Attendee

Workshop Schedule

Monday, April 29, 2019
TimeEventLocationMaterials
8:30 - 8:55Registration - ICERM 121 South Main Street, Providence RI 0290311th Floor Collaborative Space 
8:55 - 9:00Welcome - ICERM Director11th Floor Lecture Hall 
9:00 - 9:45On Combining CRF and CNN - Olga Veksler, University of Waterloo11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Computing Rolling Shutter Camera Pose via Optimized Algebraic Geometry - Tomas Pajdla, Czech Technical University in Prague11th Floor Lecture Hall
11:30 - 12:15Semidefinite Programming in Multiview Geometry - Rekha Thomas, University of Washington11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15Min-Max affine approximants and sketches. - Michael Werman, The Hebrew University of Jerusalem11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45Point-Line Minimal Problems in Complete Multi-View Visibility - Kathlén Kohn, ICERM11th Floor Lecture Hall
5:00 - 6:30Welcome Reception11th Floor Collaborative Space 
Tuesday, April 30, 2019
TimeEventLocationMaterials
9:00 - 9:45Complexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs - Renato Monteiro, Georgia Tech11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Rotation Averaging and Strong Duality - Fredrik Kahl, Chalmers University of Technology11th Floor Lecture Hall
11:30 - 12:15Approximate Message Passing Algorithms for High-dimensional Statistical Estimation in Image Processing - Cynthia Rush, Columbia University11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15Valued Constraint Satisfaction Problems - Vladimir Kolmogorov, IST Austria11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45Testing and correcting distributions over big domains - Ronitt Rubinfeld, Massachusetts Institute of Technology11th Floor Lecture Hall
Wednesday, May 1, 2019
TimeEventLocationMaterials
9:00 - 9:45Optimization for Robust Deep Learning - M. Pawan Kumar, University of Oxford11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Image segmentation methods and the use of pairwise similarities in data mining and pattern recognition - Dorit Hochbaum, UC Berkeley11th Floor Lecture Hall
11:30 - 12:15Non-Convex Relaxations for Rank Regularization - Carl Olsson, Chalmers University of Technology and Lund University11th Floor Lecture Hall
12:30 - 12:40Group Photo11th Floor Lecture Hall 
12:40 - 2:30Break for Lunch / Free Time  
2:30 - 4:00Optimization Methods in Computer Vision and Image Processing Poster Session11th Floor Collaborative Space
Thursday, May 2, 2019
TimeEventLocationMaterials
9:00 - 9:45Adversarial Training and Robust Optimization - Yair Weiss, Hebrew University of Jerusalem11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15Optimizing Jaccard, Dice, and other measures for image segmentation - Matthew Blaschko, KU Leuven11th Floor Lecture Hall
11:30 - 12:15Quantum Inspired Methods for Computer Vision - Davi Geiger, New York University11th Floor Lecture Hall
12:30 - 2:30Break for Lunch / Free Time  
2:30 - 3:15Diversity Maximization over Large Data Sets - Sepideh Mahabadi, Toyota Technological Institute at Chicago11th Floor Lecture Hall
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45Direct estimation of texture models for image segmentation - Pedro Felzenszwalb, Brown University11th Floor Lecture Hall 
Friday, May 3, 2019
TimeEventLocationMaterials
9:00 - 9:45Projective Splitting Methods for Decomposing Convex Optimization Problems - Jonathan Eckstein, Rutgers University11th Floor Lecture Hall
10:00 - 10:30Coffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15On variational methods in imaging sciences, and Hamilton-Jacobi equations - Jerome Darbon, Brown University11th Floor Lecture Hall
11:30 - 12:15Segmentation without Full Supervision - Yuri Boykov, University of Waterloo11th Floor Lecture Hall 
12:30 - 2:30Break for Lunch / Free Time  
3:30 - 4:00Coffee/Tea Break11th Floor Collaborative Space 

Request Reimbursement

Acceptable Costs
  • 1 roundtrip between your home institute and ICERM
  • Flights on U.S. or E.U. airlines – economy class to either Providence airport (PVD) or Boston airport (BOS)
  • Ground Transportation to and from airports and ICERM.
Unacceptable Costs
  • Flights on non-U.S. or non-E.U. airlines
  • Flights on U.K. airlines
  • Seats in economy plus, business class, or first class
  • Change ticket fees of any kind
  • Multi-use bus passes
  • Meals or incidentals
Advance Approval Required
  • Personal car travel to ICERM from outside New England
  • Multiple-destination plane ticket; does not include layovers to reach ICERM
  • Arriving or departing from ICERM more than a day before or day after the program
  • Multiple trips to ICERM
  • Rental car to/from ICERM
  • Flights on a Swiss, Japanese, or Australian airlines
  • Arriving or departing from airport other than PVD/BOS or home institution's local airport
  • 2 one-way plane tickets to create a roundtrip (often purchased from Expedia, Orbitz, etc.)
Reimbursement Request Form

https://icerm.brown.edu/money/

Refer to the back of your ID badge for more information. Checklists are available at the front desk.

Reimbursement Tips
  • Scanned original receipts are required for all expenses
  • Airfare receipt must show full itinerary and payment
  • ICERM does not offer per diem or meal reimbursement
  • Allowable mileage is reimbursed at prevailing IRS Business Rate and trip documented via pdf of Google Maps result
  • Keep all documentation until you receive your reimbursement!
Reimbursement Timing

6 - 8 weeks after all documentation is sent to ICERM. All reimbursement requests are reviewed by numerous central offices at Brown who may request additional documentation.

Reimbursement Deadline

Submissions must be received within 30 days of ICERM departure to avoid applicable taxes. Submissions after thirty days will incur applicable taxes. No submissions are accepted more than six months after the program end.

Associated Semester Workshops

Computer Vision
Computer Vision Image
Algebraic Vision Research Cluster
Algebraic Vision Research Cluster Image
Computational Imaging
Computational Imaging Image
Introduction to the ANTs Ecosystem
Introduction to the ANTs Ecosystem Image

Lecture Videos

Diversity Maximization over Large Data Sets

Sepideh Mahabadi
Toyota Technological Institute at Chicago (TTIC)
May 2, 2019

Valued Constraint Satisfaction Problems

Vladimir Kolmogorov
Institute of Science and Technology (IST)
April 30, 2019