- 172회 언론정보학 포럼 : 주정석 교수
- 일시 2021.03.12
- Date2021-03-19 15:53:51
3월 12일(금) 오전 10시부터 진행되는 172회 언론정보학 포럼에 대해 안내드립니다.
이번 172회 언론정보학 포럼은 온라인(ZOOM)으로만 진행되며, 아래에 포럼 접속 링크를 안내드립니다.
2021년의 첫 언론정보학 포럼에 많은 참여 부탁드립니다.
○ 주제: Ethics and Fairness in Artificial Intelligence and Deep Learning: Gender and Racial Biases in Models, Data, and Society
○ 발표자: 주정석 교수 (University of California, Los Angeles)
○ ZOOM을 통한 접속 링크: https://snu-ac-kr.zoom.us/j/83829487007
○ 시간: 3월 12일(금) 오전 10:00 ~ 11:30
○ 초록: Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports indicate that these systems may produce biased results, discriminating against people in certain demographic groups. Identification and diagnosis of such model bias, however, are challenging tasks because modern computer vision systems rely complex, black-box models whose behaviors are hard to decode. In this talk, I will first introduce our new dataset, FairFace, which can be used to measure the biases of computer vision models for face attribute classification. The dataset contains 108,501 images which are balanced race in contrast to existing public face image datasets, which are dominated by White faces. I will also discuss our new framework which allows us to measure counterfactual fairness in computer vision models. By using a generative model for face attribute manipulation, our method can synthesize new facial images varying in the dimensions of gender and race, while keeping other information intact. Such images can then be used to measure the sensitivity of a computer vision model to gender or race related cues. Using this new dataset and method, I will demonstrate the biases of several public datasets and commercial services commonly used by researchers.
○ 연사 소개: Jungseock Joo is an assistant professor in Communication at University of California, Los Angeles and a visiting researcher in Amazon Alexa AI. His research primarily focuses understanding multimodal human communication with computer vision and machine learning. His research employs various types of large scale multimodal media data such as TV news orline social media and examines how multimodal cues in these domains relate to public opinions and real world events. He has received more than $2M in extramural funding from the National Science Foundation, Hellman Foundation, Samsung, and other awards. His research has appeared in prestigious venues in both computer science and social sciences including PNAS, CVPR, ICCV, ACMMM, APSR, JoP, IJoC, and many others. He received Ph.D. in Computer Science from UCLA, M.S. in Computer Science from Columbia University, and B.S.E. in Computer Science and Engineering from Seoul National University. He was a research scientist at Facebook Applied Machine Learning & AI Research prior to joining UCLA in 2016.