Efficient Deep Learning on Model, Data, Label and Beyond
Title: Efficient Deep Learning on Model, Data, Label and Beyond
Speaker: Zhiqiang Shen, Assistant Professor at HKUST
Date: Feb. 11, Friday, 5PM
Abstract: Efficient deep learning is a broad concept that we aim to learn compressed deep models and develop training algorithms to improve the efficiency of model representations, data and label utilization, etc. In recent years, deep neural networks have been recognized as one of the most effective techniques for many learning tasks, also, in the foreseeable future the world will be populated with intelligent devices that require executable deep models on these inexpensive, low-power hardware platforms. Therefore, efficient training/inference and their learning algorithms, together with the real-world applications will be an indispensable and new hot area in both academia and industry. It is also an interdisciplinary field that deals with the ability of how machines can be developed to obtain high-level understanding from data, meanwhile, significantly reducing the number of parameters and computation requirements of deep models.
In this talk, I will introduce my recent studies that are related to the efficient deep learning on model, label and data, and its broad applications, covering the understanding of knowledge distillation and label smoothing, few-shot learning, self-supervised representation learning through image mixtures, etc.
Bio: Zhiqiang Shen currently has joined the Hong Kong University of Science and Technology (HKUST) in CSE department as a Research Assistant Professor. He was a postdoctoral researcher at CMU&MBZUAI, working with Prof Eric Xing and Prof Marios Savvides. Prior to CMU, he was a joint-training PhD student at UIUC and Fudan University, advised by Prof. Thomas Huang. His research interests span broad areas of efficient deep learning, computer vision, machine learning, etc. He has published 30+ top-tier papers on TPAMI, IJCV, ICML, ICLR, CVPR, ICCV, ECCV, AAAI, etc.