Sunday, 16th June @ Terrace Theater
- 08:30-09:00 Introduction and opening words from the organizers
- 09:00-09:30 Keynote speaker: Aude Oliva (MIT): "The Time-Machine in Your Head"
- 09:30-10:00 Spotlight presentations
- Budget-aware Semi-Supervised Semantic and Instance Segmentation. Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giró-i-Nieto
- Convolutional Neural Networks on Randomized Data. Cristian G. Ivan
- Semi-Supervised Robust Deep Neural Networks for Multi-Label Classification. Hakan Cevikalp, Burak Benligiray, Ömer Nezih Gerek, Hasan Saribas
- Joint Learning of Neural Networks via Iterative Reweighted Least Squares. Zaiwei Zhang, Xiangru Huang, Qixing Huang, Xiao Zhang, Yuan Li
- Enhancing Salient Object Segmentation Through Attention. Anuj Pahuja, Avishek Majumder, Anirban Chakraborty and R. Venkatesh Babu
- Maximally Compact and Separated Features with Regular Polytope Networks. Federico Pernici, Matteo Bruni, Claudio Baecchi, Alberto Del Bimbo
- Normal Estimation for Accurate 3D Mesh Reconstruction with Point Cloud Model Incorporating Spatial Structure. Taisuke Hashimoto, Masaki Saito
- 10:00-10:30 Coffee break + Poster presentations
- 10:30-11:00 Keynote speaker: Laurens van der Maaten (Facebook AI Research): "Making Image Recognition Work in the Real World"
- 11:00-11:30 Keynote speaker: Serena Yeung (Stanford University)
- 11:30-12:00 Keynote speaker: Laura Leal-Taixé (Technical University of Munich)
- 12:00-13:30 Lunch break
- 13:30-14:00 Keynote speaker: Chris Bregler (Google AI)
- 14:00-14:30 Keynote speaker: Alex Berg (Facebook AI Research and UNC Chapel Hill)
- 14:30-15:00 Spotlight presentations
- A Nonlinear, Noise-aware, Quasi-clustering Approach to Learning Deep CNNs from Noisy Labels. Ishan Jindal, Matthew Nokleby, Daniel Pressel, Xuewen Chen
- Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images. Shubhra Aich, Ian Stavness
- Style Augmentation: Data Augmentation via Style Randomization. Philip T.G. Jackson, Amir Atapour-Abarghouei, Stephen A.R. Bonner, Toby Breckon, Boguslaw Obara
- Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding. Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
- SANE: Towards Improved Prediction Robustness via Stochastically Activated Network Ensembles. Ibrahim Ben Daya, Mohammad Javad Shafiee, Michelle Karg, Christian Scharfenberger, Alexander Wong
- Unsupervised Learning of Paired Style Statistics for Unpaired Image Translation. Saeid Motiian, Quinn K. Jones, Stanislav Pidhorskyi, Gianfranco Doretto
- Automatic Labeling of Data for Transfer Learning. Parijat Dube, Bishwaranja Bhattacharjee, Siyu Huo, Patrick D. Watson, John Kender, Brian M. Belgodere
- 15:00-15:30 Coffee break + Poster presentations
- 15:30-16:00 Keynote speaker: Krzysztof Choromanski (Google Brain Robotics)
- 16:00-16:30 Keynote speaker: Zeynep Akata (University of Amsterdam)
- 16:30-17:00 Keynote speaker: Pierre Sermanet (Google Brain): "Self-Supervision and Play"
- 17:00-17:30 Closing remarks
Serena Yeung, Stanford University
Serena Yeung is a new Assistant Professor of Biomedical Data Science and, by courtesy, of Computer Science and of Electrical Engineering, at Stanford University. She just finished a postdoctoral fellowship in Technology for Equitable and Accessible Medicine at Harvard University, where she worked with Susan Murphy in Statistics and John Halamka in Medicine. Serena received her PhD from Stanford in 2018, where she was a member of the Artificial Intelligence Lab and advised by Fei-Fei Li in Computer Science and Arnold Milstein in Medicine. Her research has been broadly in the areas of computer vision, machine learning, and deep learning, with particular focus on video understanding and applications in healthcare. During her PhD, she was also co-instructor of Stanford's CS231N Convolutional Neural Networks for Visual Recognition course in 2017 and 2018, with Justin Johnson and Fei-Fei Li. Serena spent time at Facebook AI Research in 2016 and Google Cloud AI in 2017.
Laurens van der Maaten, Facebook AI Research
Laurens van der Maaten is a Research Scientist at Facebook AI Research in New York. Prior, he worked as an Assistant Professor at Delft University of Technology (The Netherlands) and as a post-doctoral researcher at University of California, San Diego. He received his PhD from Tilburg University (The Netherlands) in 2009. With collaborators from Cornell University, he won the Best Paper Award at CVPR 2017. He is an editorial board member of IEEE Transactions of Pattern Analysis and Machine Intelligence and is regularly serving as area chair for the NeurIPS, ICML, and CVPR conferences. Laurens is interested in a variety of topics in machine learning and computer vision.
Laura Leal-Taixé, Technical University of Munich
Prof. Laura Leal-Taixé is leading the Dynamic Vision and Learning group at the Technical University of Munich, Germany. She received her Bachelor and Master degrees in Telecommunications Engineering from the Technical University of Catalonia (UPC), Barcelona. She did her Master Thesis at Northeastern University, Boston, USA and received her PhD degree (Dr.-Ing.) from the Leibniz University Hannover, Germany. During her PhD she did a one-year visit at the Vision Lab at the University of Michigan, USA. She also spent two years as a postdoc at ETH Zurich, Switzerland and one year at the Technical University of Munich. In 2017, she won the Sofja Kovalevskaja Award of 1.65 million euros from the presitgious Humboldt Foundation for her project "socialMaps".
Chris Bregler, Google AI
Chris Bregler is a senior staff scientist and manager at Google AI. Previously, he was a professor of computer science at New York and Stanford universities, and has also worked for Hewlett Packard, Interval, “The New York Times,” Walt Disney Animation Studios, and Lucasfilm’s VFX and animation studio Industrial Light & Magic. He received an Academy Award for science and technology in 2016, and in 2008 he won the IEEE Longuet-Higgins Prize for Fundamental Contributions in Computer Vision That Have Withstood the Test of Time.
Zeynep Akata, University of Amsterdam
Zeynep Akata is an Assistant Professor with the University of Amsterdam in the Netherlands, Scientific Manager of the Delta Lab and a Senior Researcher at the Max Planck Institute for Informatics in Germany. She holds a BSc degree from Trakya University (2008), MSc degree from RWTH Aachen (2010) and a PhD degree from University of Grenoble (2014). After completing her PhD at the INRIA Rhone Alpes with Prof. Dr. Cordelia Schmid, she worked as a post-doctoral researcher at the Max Planck Institute for Informatics with Prof. Dr. Bernt Schiele and a visiting researcher with Prof Trevor Darrell at UC Berkeley. Her research interests include machine learning that combine vision and language for the task of explainable artificial intelligence (XAI).
Pierre Sermanet, Google Brain
Pierre Sermanet is a Research Scientist at Google Brain. He obtained his PhD from NYU in 2013 under the supervision of Yann LeCun. Pierre has published on various topics in the fields of computer vision, robotics and self-supervised learning.
Aude Oliva, MIT
After a French baccalaureate in Physics and Mathematics and a B.Sc. in Psychology (minor in Philosophy), Aude Oliva received two M.Sc. degrees –in Experimental Psychology, and in Cognitive Science and a Ph.D from the Institut National Polytechnique of Grenoble, France. She joined the MIT faculty in the Department of Brain and Cognitive Sciences in 2004, the MIT Computer Science and Artificial Intelligence Laboratory - CSAIL - in 2012, the MIT-IBM Watson AI Lab in 2017, and the leadership of the Quest for Intelligence in 2018. She is also affiliated with the Athinoula A. Martinos Imaging Center at the McGoven Institute for Brain Research MIT, and the MIT CSAIL Initiative Systems That Learn.
Alex Berg, Facebook AI Research and UNC Chapel Hill
Alex Berg's research concerns computational visual recognition and machine learning for computer and human vision. He co-founded and co-organized the ImageNet Large Scale Visual Recognition Challenge, and co-organized the first Large-Scale Learning for Vision workshop. He is currently a research scientist at Facebook AI and an Associate Professor at UNC Chapel Hill. His work received the Marr Prize in 2013, the Mark Everingham Prize for community contributions in 2016, and the Helmholtz Prize for work that stood the test of time in 2017.
Krzysztof Choromanski, Google Brain Robotics
Krzysztof Choromanski is a research scientist at Google Brain Robotics Team in New York and an adjunct assistant professor at Columbia University. He works on a diverse set of topics in machine learning, reinforcement learning (RL) and robotics ranging from combinatorial methods, structured transforms (with applications in compressed neural networks, hashing/dimensionality reduction techniques and recurrent neural network-based architectures) to evolution strategy (ES) algorithms. In the latter setting he proposed several novel scalable ES methods for learning RL policies using new Monte Carlo algorithms and new policy representations. He is recently interested in further improving sampling complexity of these methods via new guided ES techniques as well as curiosity-driven exploration strategies.