(Virtual)
Dataset distillation and Learning to see by looking at noise
Dr. Antonio Torralba, Delta Electronics Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology (MIT) and Head of the AI+D faculty in the EECS department.
Short Abstract: The importance of data in modern computer vision is hard to overstate. The ImageNet dataset, with its millions of labelled images, is widely thought to have spurred the era of deep learning, and since then the scale of vision datasets has been increasing at a rapid pace. These datasets come with costs: curation is expensive, and they inherit human biases. To counter these costs, interest has surged in unsupervised learning as it avoids the curation efforts, or using virtual worlds. In this talk I will cover two projects that try to reduce the size of datasets needed to train computer vision systems. I will first talk about Dataset distillation is the task of synthesizing a small dataset such that models trained on it achieve high performance on the original large dataset. A good small distilled dataset is not only useful in dataset understanding, but has various applications (e.g., continual learning, privacy, neural architecture search, etc.). Finally, I will go a step further and ask if we can do away with real image datasets entirely, instead learning from noise processes. Noise processes produce images that are reminiscent of abstract art, where images contain textures and shapes, but there are no recognizable objects. Our findings show that good performance on real images can be achieved even with training images that are far from realistic.
For more information:
Dataset distillation – https://georgecazenavette.github.io/mtt-distillation/
Learning from noise – https://mbaradad.github.io/learning_with_noise/
Short bio: Antonio Torralba is the Delta electronics Professor and head of the AI+D faculty at the Department of Electrical Engineering and Computer Science (EECS) at the Massachusetts Institute of Technology (MIT). From 2017 to 2020, he was the MIT director of the MIT-IBM Watson AI Lab, and, from 2018 to 2020, the inaugural director of the MIT Quest for Intelligence, a MIT campus-wide initiative to discover the foundations of intelligence. He is also member of CSAIL and the Center for Brains, Minds and Machines. He received the degree in telecommunications engineering from Telecom BCN, Spain, in 1994 and the Ph.D. degree in signal, image, and speech processing from the Institut National Polytechnique de Grenoble, France, in 2000. From 2000 to 2005, he spent postdoctoral training at the Brain and Cognitive Science Department and the Computer Science and Artificial Intelligence Laboratory, MIT, where he is now a professor. Prof. Torralba has served as program chair for the Computer Vision and Pattern Recognition conference in 2015. He received the 2008 National Science Foundation (NSF) Career award, the best student paper award at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in 2009, the 2010 J. K. Aggarwal Prize from the International Association for Pattern Recognition (IAPR), the 2017 Frank Quick Faculty Research Innovation Fellowship, the Louis D. Smullin (’39) Award for Teaching Excellence, the 2020 PAMI Mark Everingham Prize, and was named 2021 AAAI fellow. In 2021, he was awarded the Inaugural Thomas Huang Memorial Prize by the PAMITC. In 2022, he was invested Honoris Causa doctor by the Universitat Politècnica de Catalunya – BarcelonaTech (UPC).