معرفی
Michael Maire is an Associate Professor in the Department of Computer Science at the University of Chicago, with a courtesy appointment at the Toyota Technological Institute at Chicago (TTIC). His research focuses on computer vision, machine learning, and deep learning, particularly in neural network architectures, optimization, and self-supervised learning. Prior to UChicago, he held roles at TTIC and Caltech, and earned his Ph.D. from UC Berkeley in 2009.
His work spans perceptual organization, object recognition, and representation learning. Key contributions include the Microsoft COCO dataset, fractalnet architectures, and spectral embedding techniques for segmentation and figure/ground organization. He advises students on topics like efficient network growth, sparsification, and contrastive learning.
He co-leads the Machine Learning Group at UChicago and contributes to the CERES Center for Unstoppable Computing. His research has been published in top venues like CVPR, ICCV, and NeurIPS, with over 30 peer-reviewed articles since 2004. Teaching includes courses on computer vision and deep learning fundamentals.
