Past talk · AI/ML Seminar Series
From Heatmaps to Structural and Counterfactual Explanations
Associate Professor of Electrical Engineering and Computer Science, Oregon State University
- Date & time
- Monday, January 8, 2024 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
This talk will focus on our endeavors in the past few years on explaining deep image models. Realizing that an important missing piece for explaining neural networks is a reliable heatmap visualization tool, we developed I-GOS and iGOS++ which optimize with integrated gradients to avoid local optima in heatmap generations and improve performance in high-resolution heatmaps. 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. Finally, we present results traversing the latent space of variational autoencoders and generative adversarial networks (GANs), generating high-quality counterfactual explanations that visually show how to change one image so that CNNs predict them as another category.
About the speaker
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, (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 70 papers in computer vision, machine learning and natural language processing.