Wednesday, October 13, 2021 - 1:00pm to 2:00pm
CORD 1109 or Zoom:

Speaker Information

Fuxin Li
Associate Professor
Computer Science
Oregon State University


This talk will focus on our endeavors in the past few years in terms of explaining image classifiers. Realizing that an important missing piece for explaining neural networks is a reliable heatmap visualization tool, we developed I-GOS and iGOS++ utilizing integrated gradients to avoid local optima in heatmap generations and improve performance in high-resolution heatmaps. Especially, iGOS++ was able to discover that deep classifiers trained on COVID-19 X-ray images wrongly focus on the characters printed on the image and could produce erroneous solutions. This shows the utility of explanation in "debugging" the classifiers.

During the development of those visualizations, we realize that for a significant number of images, the classifier has multiple different paths to reach a confident prediction, this leads to our recent development of structural attention graphs, an approach that utilizes beam search to locate multiple coarse heatmaps for a single image, and compactly visualizes a set of heatmaps by capturing how different combinations of image regions impact the confidence of a classifier. A user study shows significantly better capability of users to answer counterfactual questions when presented with SAG versus conventional heatmaps.

Speaker Bio

Fuxin Li is currently an associate professor in the School of Electrical Engineering and Computer Science at Oregon State University. Before that, he has held research positions in University of Bonn and Georgia Institute of Technology. He had obtained a Ph.D. degree in the Institute of Automation, Chinese Academy of Sciences in 2009. He has won an NSF CAREER award, an Amazon Research Award, an Oregon State University College of Engineering Research Award, (co-)won the PASCAL VOC semantic segmentation challenges from 2009-2012, and led a team to the 4th place finish in the DAVIS Video Segmentation challenge 2017. He has published more than 60 papers in computer vision, machine learning and natural language processing. His main research interests are deep learning, video object segmentation, multi-target tracking, point cloud deep networks, uncertainty estimation in deep learning and human understanding of deep learning.