[Lunch Talk] Deep metric learning for retrieval and clustering
Learning to measure the similarity among arbitrary groups of data is of great practical importance, and is used in a variety of tasks such as feature based retrieval, clustering, near duplicate detection, verification, feature matching, domain adaptation, weakly supervised learning, etc. In this talk, we'll explore the state of the art in deep metric learning with applications on retrieval, clustering, and unsupervised domain adaptation.
Hyun Oh Song is an assistant professor in the Department of Computer Science and Engineering at Seoul National University. Before SNU, he was a full-time research scientist at Google Research, in Mountain View, where he worked on machine learning and deep learning. Before Google, he was a postdoctoral fellow in SAIL in the Computer Science Department at Stanford University. Hyun Oh finished his Ph.D in Computer Science at UC Berkeley in late 2014. His graduate study was fully supported by Samsung Lee Kun Hee Scholarship Foundation (Now Samsung Scholarship Foundation) for five years. In 2013, he spent time at LEAR, INRIA as a visiting student researcher and at IBM Research as a research intern. His research interests are in machine learning, optimization, deep learning, computer vision, and robotics. Broadly, he is interested in solving challenging problems in artificial intelligence. Also, he is an invited reviewer for NIPS, ICML, SIGGRAPH, TPAMI, IJCV, RSS, ICCV, ECCV, CVPR, CVIU, and ICRA. He has an academic website at http://cs.stanford.edu/~hsong.