Timezone: »
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.
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 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)
-
2022 Poster: A Study of Face Obfuscation in ImageNet »
Wed. Jul 20th through Thu the 21st Room Hall E #923
More from the Same Authors
-
2023 : Invited Talk 2: Olga Russakovsky (Princeton University) »
Olga Russakovsky -
2021 Poster: Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline »
Ankit Goyal · Hei Law · Bowei Liu · Alejandro Newell · Jia Deng -
2021 Poster: Directional Bias Amplification »
Angelina Wang · Olga Russakovsky -
2021 Spotlight: Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline »
Ankit Goyal · Hei Law · Bowei Liu · Alejandro Newell · Jia Deng -
2021 Spotlight: Directional Bias Amplification »
Angelina Wang · Olga Russakovsky -
2021 Poster: SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies »
Jim Fan · Guanzhi Wang · De-An Huang · Zhiding Yu · Li Fei-Fei · Yuke Zhu · Anima Anandkumar -
2021 Spotlight: SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies »
Jim Fan · Guanzhi Wang · De-An Huang · Zhiding Yu · Li Fei-Fei · Yuke Zhu · Anima Anandkumar -
2020 Poster: PackIt: A Virtual Environment for Geometric Planning »
Ankit Goyal · Jia Deng -
2019 : Olga Russakovsky »
Olga Russakovsky -
2019 Poster: Learning to Prove Theorems via Interacting with Proof Assistants »
Kaiyu Yang · Jia Deng -
2019 Oral: Learning to Prove Theorems via Interacting with Proof Assistants »
Kaiyu Yang · Jia Deng -
2018 Poster: Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? »
Zhengyuan Zhou · Panayotis Mertikopoulos · Nicholas Bambos · Peter Glynn · Yinyu Ye · Li-Jia Li · Li Fei-Fei -
2018 Oral: Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? »
Zhengyuan Zhou · Panayotis Mertikopoulos · Nicholas Bambos · Peter Glynn · Yinyu Ye · Li-Jia Li · Li Fei-Fei