HLA-Face: Joint High-Low Adaptation for Low Light Face Detection

TL;DR

HLA-Face introduces a joint high-low adaptation framework that effectively transfers face detection capabilities from normal to low light conditions without requiring low-light face annotations.

Contribution

The paper proposes a novel bidirectional low-level and multi-task high-level adaptation framework for low-light face detection, reducing the need for annotated low-light data.

Findings

Outperforms state-of-the-art low-light face detection methods

Effective adaptation without dark face labels

Utilizes existing normal light datasets for low-light detection

Abstract

Face detection in low light scenarios is challenging but vital to many practical applications, e.g., surveillance video, autonomous driving at night. Most existing face detectors heavily rely on extensive annotations, while collecting data is time-consuming and laborious. To reduce the burden of building new datasets for low light conditions, we make full use of existing normal light data and explore how to adapt face detectors from normal light to low light. The challenge of this task is that the gap between normal and low light is too huge and complex for both pixel-level and object-level. Therefore, most existing low-light enhancement and adaptation methods do not achieve desirable performance. To address the issue, we propose a joint High-Low Adaptation (HLA) framework. Through a bidirectional low-level adaptation and multi-task high-level adaptation scheme, our HLA-Face outperforms state-of-the-art methods even without using dark face labels for training. Our project is publicly available at https://daooshee.github.io/HLA-Face-Website/