Department of Computer Science and the College
Michael Maire’s research interests span computer vision, with an emphasis on perceptual organization and object recognition, and deep learning, with a focus on neural network architectures. His work has centered around the architectures of deep convolutional neural networks (CNNs), their underlying structures, and the modifications that will help apply deep learning to new, more complicated applications. In addition, he also contributes to the data that CNNs are tested with, through his work on the Common Objects in Context (COCO) data set. Comprised of over 330,000 images of complex everyday scenes, COCO provides a target for scientists to test new methods in object detection, captioning, and segmentation.
His research has been presented at the IEEE (Institute of Electrical and Electronics Engineers) Conference on Computer Vision and Pattern Recognition and the International Conference on Learning Representations.
Maire received a PhD in computer science from the University of California, Berkeley, and was a senior postdoctoral scholar at the California Institute of Technology. Most recently, he was a research assistant professor at the Toyota Technological Institute at Chicago, where he maintains a courtesy appointment.