Course Summary

This graduate course is especially meant for Ph.D. students who have basic familiarity with computer vision, image processing, and machine learning and want to upsurge their knowledge and machinery to the state-of-the-art, with direct utility in their own research.

The topic of attention is the challenge of computer vision by learning. We address the theoretical foundations of computer vision in conjunction with machine learning and present algorithms that achieve state-of-the-art performance while maintaining efficient execution with minimal supervision. This year we explain and emphasize on computer vision by deep learning, including challenges like image classification by data-efficient convolutional neural networks, face generation by Generative Adversarial Networks, action recognition with point-supervision, and explainability by vision and language embeddings. We give an overview of the latest developments and future trends in the field on the basis of several recent challenges, and we indicate how to obtain improvements in the near future.

Course Registration

Course registration is handled by the ASCI research school, via this form. Note that the number of seats for this course is limited.

Lab requirements: bring your own device

For the lab, you are expected to bring your own device, either a laptop with a good GPU or a laptop that can connect to a workstation with a good GPU. In case you cannot connect to a GPU, you should make a CoLAB Google Account and make sure you can run a GPU powered notebook (You can turn the GPU on by the following steps: Edit->Notebook settings->Hardware accelerator->GPU)

Course Schedule

Monday April 1, 2019: Fundamentals

TimeRoom TopicLecturer
0900-0930CWI - Z009 EulerzaalWelcome with coffee and tea
0930-1010CWI - Z009 EulerzaalIntroduction, observables, invarianceCees Snoek
1010-1020Short break
1020-1100CWI - Z009 EulerzaalFrom perceptron to AlexNetCees Snoek
1100-1130Break
1130-1215CWI - Z009 EulerzaalVision in the deep learning eraEfstratios Gavves
1215-1330Lunch break
1330-1700CWI - Z009 EulerzaalLab session - day 1: MLP 

Tuesday April 2, 2019: Computer vision by deep learning

TimeRoom TopicLecturer
0900-0930CWI - Z009 EulerzaalWelcome with coffee and tea
0930-1010CWI - Z009 EulerzaalDeep learning beyond classificationEfstratios Gavves
1010-1020Short break
1020-1100CWI - Z009 EulerzaalDeep learning beyond classificationEfstratios Gavves
1100-1130Break
1130-1215CWI - Z009 EulerzaalExplainable computer visionZeynep Akata
1215-1330Lunch break
1330-1700CWI - Z009 EulerzaalLab session - day 2: CNN 

Wednesday April 3, 2019: Machine learning for computer vision

TimeRoom TopicLecturer
0900-0930CWI - Z009 EulerzaalWelcome with coffee and tea
0930-1030CWI - Z009 EulerzaalEquivariant deep learningTaco Cohen
1030-1100Break
1100-1200CWI - Z009 EulerzaalRecent pogress in generative modelsTim Salimans
1200-1330Lunch break
1330-1700CWI - Z009 EulerzaalLab session - day 3: RNN 

Thursday April 4, 2019: Computer video by learning

TimeRoom TopicLecturer
0900-0930CWI - Z009 EulerzaalWelcome with coffee and tea
0930-1010CWI - Z009 EulerzaalVideo representation learningCees Snoek
1010-1020Short break
1020-1100CWI - Z009 EulerzaalVideo and language learningCees Snoek
1100-1130Break
1130-1215CWI - Z009 EulerzaalWeakly-supervised video recognitionPascal Mettes
1215-1330Lunch break
1330-1700CWI - Z009 EulerzaalLab session - day 4: GAN  

Friday April 5, 2019: Invited tutorial by Laurens van der Maaten

TimeRoom TopicLecturer
0900-0930Cafe Polder - PolderzaalWelcome with coffee and tea
0930-1045Cafe Polder - PolderzaalDeveloping efficient convolutional networks (and training them at scale)Laurens van der Maaten
1045-1115Break
1115-1215Cafe Polder - PolderzaalFrom visual recognition to visual understandingLaurens van der Maaten
1215-1230Closing


Invited tutorial

  • Laurens van der Maaten

    is a Research Scientist at Facebook AI Research in New York, working on machine learning and computer vision. Before, he worked as an Assistant Professor at Delft University of Technology, as a post-doctoral researcher at UC San Diego, and as a Ph.D. student at Tilburg University. He is interested in a variety of topics in machine learning and computer vision.

Lecturers

  • Cees Snoek

    is full professor in computer science at the University of Amsterdam, where he heads the Intelligent Sensory Information Systems Lab. He is also a director of the QUVA Lab, the joint research lab of Qualcomm and the University of Amsterdam on deep learning and computer vision. He was a visiting scientist at Carnegie Mellon University, Pittsburgh and the University of California, Berkeley. His research interest is video and image understanding by computer vision and machine learning.

  • Efstratios Gavves

    is an Assistant Professor with the University of Amsterdam in the Netherlands. He received his Ph.D. in 2014 at the University of Amsterdam. He was a post-doctoral researcher at the KU Leuven from 2014 - 2015. He has authored several papers in major computer vision and machine learning conferences and journals. His research interests include statistical and deep learning with applications on computer vision.

Guest Lecturers

  • Zeynep Akata

    is an Assistant Professor with the University of Amsterdam and a Senior Researcher at the Max Planck Institute for Informatics since 2017. She holds a MSc degree from RWTH Aachen (2010) and a PhD degree from INRIA Rhone Alpes (2014). Between 2014-2017 she was a post-doctoral researcher at the MPI for Informatics and at UC Berkeley. She is the 2014 recipient of Lise Meitner Award for Excellent Women in Computer Science. Her research interests include vision and language for explainable artificial intelligence.

  • Taco Cohen

    is a machine learning research scientist at Qualcomm AI Research and wrapping up his PhD at the University of Amsterdam, supervised by prof. Max Welling. His research is focused on understanding and improving deep representation learning. He has done internships at Google Deepmind (working with Geoff Hinton) and OpenAI. He was named one of MIT techreview’s 35 innovators under 35 in 2018.

  • Tim Salimans

    is a Machine Learning research scientist at Google Brain Amsterdam working on generative modeling, semi-supervised and unsupervised deep learning, and reinforcement learning.

  • Pascal Mettes

    is a postdoctoral researcher at the University of Amsterdam. He received his PhD in 2017 at the University of Amsterdam and was a visiting scientist at Columbia University in 2016. His research interests are in computer vision, with a focus on video understanding and learning from limited supervision.