Abstract:

We are interested in learning visual representations that are discriminative for semantic image understanding tasks such as object classification, detection, and segmentation in images/videos. A common approach to obtain such features is to use supervised learning. However, this requires manual annotation of images, which is costly, ambiguous, and prone to errors. In contrast, self-supervised feature learning methods exploiting unlabeled data can be more scalable and flexible. I will present some of our recent work on using similarity between a random set of images to learn rich visual representations. More specifically, I will talk about learning representations by grouping similar images, iteratively distilling from an ensemble model to a student model, and also compressing representations. In the end, I will talk about some of our recent work on adversarial robustness of such deep models.

Bio: Hamed Pirsiavash is an associate professor at the University of California, Davis. Prior to this, he was an associate professor at the University of Maryland Baltimore County and a postdoctoral research associate at MIT. He obtained his PhD at the University of California Irvine. He does research in the intersection of computer vision and machine learning. More specifically, he is interested in self-supervised representation learning and adversarial robustness of deep models.

Organizer: Hossein Azizpour