A Study of Face Obfuscation in ImageNet

TL;DR

This study investigates how face obfuscation techniques affect the performance of image recognition models on ImageNet, showing minimal accuracy loss and supporting privacy-preserving visual recognition.

Contribution

It provides the first comprehensive analysis of face obfuscation impact on ImageNet recognition accuracy and transfer learning, demonstrating feasibility for privacy-aware visual AI.

Findings

Face obfuscation minimally impacts recognition accuracy (<= 1.0%).

Features learned on obfuscated images are equally transferable.

Supports privacy-preserving approaches in visual recognition.

Abstract

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.