Privacy-preserving Online AutoML for Domain-Specific Face Detection

TL;DR

This paper introduces HyperFD, a privacy-preserving online AutoML framework for domain-specific face detection that leverages meta-features and continual learning to improve configuration recommendations without exposing raw data.

Contribution

The paper proposes a novel privacy-preserving AutoML approach using meta-features and continual learning for face detection, addressing data privacy and sequential task adaptation.

Findings

HyperFD effectively predicts configurations without raw data exposure.

The framework improves over time by learning from previous tasks.

Experiments show HyperFD's superior performance and efficiency.

Abstract

Despite the impressive progress of general face detection, the tuning of hyper-parameters and architectures is still critical for the performance of a domain-specific face detector. Though existing AutoML works can speedup such process, they either require tuning from scratch for a new scenario or do not consider data privacy. To scale up, we derive a new AutoML setting from a platform perspective. In such setting, new datasets sequentially arrive at the platform, where an architecture and hyper-parameter configuration is recommended to train the optimal face detector for each dataset. This, however, brings two major challenges: (1) how to predict the best configuration for any given dataset without touching their raw images due to the privacy concern? and (2) how to continuously improve the AutoML algorithm from previous tasks and offer a better warm-up for future ones? We introduce "HyperFD", a new privacy-preserving online AutoML framework for face detection. At its core part, a novel meta-feature representation of a dataset as well as its learning paradigm is proposed. Thanks to HyperFD, each local task (client) is able to effectively leverage the learning "experience" of previous tasks without uploading raw images to the platform; meanwhile, the meta-feature extractor is continuously learned to better trade off the bias and variance. Extensive experiments demonstrate the effectiveness and efficiency of our design.