Title: Deeply Explainable Artificial Intelligence
Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text; contemporary vision-language models can describe image content but fail to take into account class-discriminative image aspects which justify visual predictions. In this talk, I will present my past and current work on Explainable Artificial Intelligence in that (1) how our models focus on discriminating properties of the visible object, jointly predict a class label, and explain why the predicted label is appropriate for the image. (2) how we offer both image-based visualization of attention weights and text-based generation of post-hoc justifications of classification decisions and (3) how our models mention phrases that are grounded in the image and how we generate counterfactual explanations.
Dr. Zeynep Akata is an Assistant Professor with the University of Amsterdam in the Netherlands, Scientific Manager of the Delta Lab and a Senior Researcher at the Max Planck Institute for Informatics in Germany. She holds a BSc degree from Trakya University (2008), MSc degree from RWTH Aachen (2010) and a PhD degree from University of Grenoble (2014). After completing her PhD at the INRIA Rhone Alpes with Prof. Dr. Cordelia Schmid, she worked as a post-doctoral researcher at the Max Planck Institute for Informatics with Prof. Dr. Bernt Schiele and a visiting researcher with Prof Trevor Darrell at UC Berkeley. Her research interests include machine learning combined with combine vision and language for the task of explainable artificial intelligence (XAI). She is a recipient of Lise-Meitner Award for Excellent Women in Computer Science in 2014 from Max Planck Society.
Title: Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder
Computer vision has made impressive gains through the use of deep learning models, trained with large-scale labeled data. However, labels require expertise and curation and are expensive to collect. Even worse, direct semantic supervision often leads the learning algorithms “cheating” and taking shortcuts, instead of actually doing the work. In this talk, I will briefly summarize several of my group’s efforts to combat this using self-supervision, meta-supervision, and curiosity — all ways of using the data as its own supervision. Applications in image synthesis will be shown, including, #pix2pix and #cycleGAN.
Alexei Efros is a professor of Electrical Engineering and Computer Sciences at UC Berkeley. Before 2013, he was nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems where large quantities of unlabeled visual data are readily available. Efros received his PhD in 2003 from UC Berkeley. He is a recipient of the Sloan Fellowship (2008), Guggenheim Fellowship (2008), SIGGRAPH Significant New Researcher Award (2010), 3 Helmholtz Test-of-Time Prizes (1999,2003,2005), and the ACM Prize in Computing (2016).