Aharon Bar Hillel (Microsoft Research)
Tuesday, 26.1.2016, 11:30
Training accurate visual classifiers from large data sets critically depend on learning the right representation for the problem. In this talk, I will discuss a representation learning framework based on an iterative interaction of two components: a feature generator suggesting candidate features, and a feature selector choosing among them. In the feature selector role, I will present a feature selection algorithm for Support Vector Machines (SVMs) enabling selection among hundreds of thousands of features, while maintaining the accuracy of computationally expensive wrapper methods. For the feature generator, I will discuss two main examples: part-based feature generation for human detection, and sparse feature generation for object recognition under severe test-time speed constraints. In both examples state of the art classifiers (at the time of submission) were learned. Specifically the sparse classifiers are currently the state of the art for visual classification with a tight computational budget.
Short bio: Aharon Bar Hillel is a researcher at Microsoft Research ATLI (Advanced Technical Labs Israel) since 2012. He received his Ph.D from The Hebrew University of Jerusalem in 2006, focusing on machine learning and computer vision. Since then he has been doing machine learning and computer vision oriented research at Intel Research (2006-2008) and at GM Research (2009-2012). He is interested in learning representation for machine learning tasks, including distance function learning, feature selection and synthesis, and deep learning.