Timezone: »

 
Spotlight
A Study of Face Obfuscation in ImageNet
Kaiyu Yang · Jacqueline Yau · Li Fei-Fei · Jia Deng · Olga Russakovsky

Wed Jul 20 07:45 AM -- 07:50 AM (PDT) @ Room 318 - 320
in Social Aspects/MISC »

Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy protection; nevertheless, object recognition research typically assumes access to complete, unobfuscated images. In this paper, we explore the effects of face obfuscation on the popular ImageNet challenge visual recognition benchmark. Most categories in the ImageNet challenge are not people categories; however, many incidental people appear in the images, and their privacy is a concern. We first annotate faces in the dataset. Then we demonstrate that face obfuscation has minimal impact on the accuracy of recognition models. Concretely, we benchmark multiple deep neural networks on obfuscated images and observe that the overall recognition accuracy drops only slightly (<= 1.0%). Further, we experiment with transfer learning to 4 downstream tasks (object recognition, scene recognition, face attribute classification, and object detection) and show that features learned on obfuscated images are equally transferable. Our work demonstrates the feasibility of privacy-aware visual recognition, improves the highly-used ImageNet challenge benchmark, and suggests an important path for future visual datasets. Data and code are available at https://github.com/princetonvisualai/imagenet-face-obfuscation.

Keywords: APP: Computer Vision · Social Aspects · SA: Everything Else · SA: Privacy-preserving Statistics and Machine Learning · SA: Fairness, Equity, Justice and Safety

Author Information

Kaiyu Yang (Princeton University)

Kaiyu Yang is a Ph.D. student in the Department of Computer Science at Princeton University, where he works with Prof. Jia Deng in the Princeton Vision & Learning Lab. He is interested in computer vision and artificial intelligence in general. His current research focuses on how machine learning techniques can be applied to solve theorem proving—a long-standing research area that was dominated by formal methods. Prior to that, He worked on human pose estimation, action detection, and visual relationship understanding. He received his master’s degree from the University of Michigan and his bachelor’s degree from Tsinghua University.

Jacqueline Yau (Stanford University)
Jacqueline Yau

Jacqueline Yau was a Master's student in Computer Science at Stanford University, obtaining her degree recently. She is interested in computer vision, graph representation, and general machine learning. She has worked on symmetry detection in objects, physics simulation, and the intersection of vision and audio. Currently she is working at Apple as a Machine Learning Engineer. She also received her Bachelor's degree with departmental honors in Computer Science at Stanford University.

Li Fei-Fei (Stanford University)
Jia Deng (Princeton University)
Olga Russakovsky (Princeton University)

Dr. Olga Russakovsky is an Assistant Professor in the Computer Science Department at Princeton University. Her research is in computer vision, closely integrated with the fields of machine learning, human-computer interaction and fairness, accountability and transparency. She has been awarded the AnitaB.org's Emerging Leader Abie Award in honor of Denice Denton in 2020, the CRA-WP Anita Borg Early Career Award in 2020, the MIT Technology Review's 35-under-35 Innovator award in 2017, the PAMI Everingham Prize in 2016 and Foreign Policy Magazine's 100 Leading Global Thinkers award in 2015. In addition to her research, she co-founded and continues to serve on the Board of Directors of the AI4ALL foundation dedicated to increasing diversity and inclusion in Artificial Intelligence (AI). She completed her PhD at Stanford University in 2015 and her postdoctoral fellowship at Carnegie Mellon University in 2017.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors