Privacy-Preserving Object Detection & Localization Using Distributed Machine Learning: A Case Study of Infant Eyeblink Conditioning
This work addresses privacy concerns in medical and psychological research, specifically for infant eyeblink conditioning, by enabling distributed learning without data sharing, though it is incremental as it adapts existing algorithms to a distributed setting.
The paper tackles the problem of training object detection and localization models on sensitive data like infant facial images while preserving privacy, by proposing novel distributed training algorithms (MWMA for HOG-based L-SVM and WBA for ERT) that avoid sharing raw data, resulting in accuracy increases of 0.9% and 8% respectively compared to traditional or single-node methods.
Distributed machine learning is becoming a popular model-training method due to privacy, computational scalability, and bandwidth capacities. In this work, we explore scalable distributed-training versions of two algorithms commonly used in object detection. A novel distributed training algorithm using Mean Weight Matrix Aggregation (MWMA) is proposed for Linear Support Vector Machine (L-SVM) object detection based in Histogram of Orientated Gradients (HOG). In addition, a novel Weighted Bin Aggregation (WBA) algorithm is proposed for distributed training of Ensemble of Regression Trees (ERT) landmark localization. Both algorithms do not restrict the location of model aggregation and allow custom architectures for model distribution. For this work, a Pool-Based Local Training and Aggregation (PBLTA) architecture for both algorithms is explored. The application of both algorithms in the medical field is examined using a paradigm from the fields of psychology and neuroscience - eyeblink conditioning with infants - where models need to be trained on facial images while protecting participant privacy. Using distributed learning, models can be trained without sending image data to other nodes. The custom software has been made available for public use on GitHub: https://github.com/SLWZwaard/DMT. Results show that the aggregation of models for the HOG algorithm using MWMA not only preserves the accuracy of the model but also allows for distributed learning with an accuracy increase of 0.9% compared with traditional learning. Furthermore, WBA allows for ERT model aggregation with an accuracy increase of 8% when compared to single-node models.