Privacy-preserving Object Detection
Not on the map. Why?
Abstract (arXiv)
Privacy considerations and bias in datasets are quickly becoming high-priority issues that the computer vision community needs to face. So far, little attention has been given to practical solutions that do not involve collection of new datasets. In this work, we show that for object detection on COCO, both anonymizing the dataset by blurring faces, as well as swapping faces in a balanced manner along the gender and skin tone dimension, can retain object detection performances while preserving privacy and partially balancing bias.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 11 Mar 2021.
Builds on
19 of 29 references.
References · 19
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2017Mask R-CNNcited by 7,259
- 2020Extracting Training Data from Large Language Modelscited by 2,144
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
- 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
- 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
- 2020Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biasescited by 107
- 2021A Study of Face Obfuscation in ImageNetcited by 83
7 more
- 2016A causal framework for discovering and removing direct and indirect discriminationcited by 71
- 2018Learning to Anonymize Faces for Privacy Preserving Action Detectioncited by 63
- 2017Natural and Effective Obfuscation by Head Inpaintingcited by 60
- 2018Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Studycited by 48
- 2016Privacy-Preserving Human Activity Recognition from Extreme Low Resolutioncited by 43
- 2017Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Imagescited by 24
- 2018Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learningcited by 15
Built on by
Citing papers per year: 2022: 1.
1 paper.