Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
High-performance visual recognition systems generally require a large collection of labeled images to train. The expensive data curation can be an obstacle for improving recognition performance. Sharing more data allows training for better models. But personal and private information in the data prevent such sharing. To promote sharing visual data for learning a recognition model, we propose to obfuscate the images so that humans are not able to recognize their detailed contents, while machines can still utilize them to train new models. We validate our approach by comprehensive experiments on three challenging visual recognition tasks; image classification, attribute classification, and facial landmark detection on several datasets including SVHN, CIFAR10, Pascal VOC 2012, CelebA, and MTFL. Our method successfully obfuscates the images from humans recognition, but a machine model trained with them performs within about 1% margin (up to 0.48%) of the performance of a model trained with the original, non-obfuscated data.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeFacial Landmark DetectionGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
Social media platforms are being increasingly used by malicious actors to share unsafe content, such as images depicting sexual activity, cyberbullying, and self-harm. Consequently, major platforms use artificial intelli…
counterfactualCounterfactual ExplanationLanguage ModelingLanguage Modelling+1Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images
Images convey a broad spectrum of personal information. If such images are shared on social media platforms, this personal information is leaked which conflicts with the privacy of depicted persons. Therefore, we aim for…
Obfuscating Gender in Social Media Writing
Embedding Java Classes with code2vec: Improvements from Variable Obfuscation
Automatic source code analysis in key areas of software engineering, such as code security, can benefit from Machine Learning (ML). However, many standard ML approaches require a numeric representation of data and cannot…
Code ClassificationMethod name predictionSliceIt! -- A Dual Simulator Framework for Learning Robot Food Slicing
Cooking robots can enhance the home experience by reducing the burden of daily chores. However, these robots must perform their tasks dexterously and safely in shared human environments, especially when handling dangerou…
Reinforcement Learning (RL)