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

arXiv: https://arxiv.org/abs/2104.01984 · HTML: https://mlsanity.com/paper/2104.01984/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 60 references that are in the map.
- First posted on arXiv 5 Apr 2021.

## Builds on (most cited first, 30 of 46)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)

## Built on by (most cited first, 28 of 28)

- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [Instance Segmentation in the Dark](https://mlsanity.com/paper/2304.14298/) (2023)
- [Human Pose Estimation in Extremely Low-Light Conditions](https://mlsanity.com/paper/2303.15410/) (2023)
- [Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision](https://mlsanity.com/paper/2112.04719/) (2021)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision](https://mlsanity.com/paper/2308.03594/) (2023)
- [Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2312.01220/) (2023)
- [Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data](https://mlsanity.com/paper/2211.04700/) (2022)
- [Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields](https://mlsanity.com/paper/2303.05807/) (2023)
- [TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2503.08168/) (2025)
- [SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency](https://mlsanity.com/paper/2305.08053/) (2023)
- [Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2405.11478/) (2024)
- [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022)
- [From Enhancement to Understanding: Build a Generalized Bridge for Low-light Vision via Semantically Consistent Unsupervised Fine-tuning](https://mlsanity.com/paper/2507.08380/) (2025)
- [Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation](https://mlsanity.com/paper/2309.03548/) (2023)
- [Leveraging Content and Context Cues for Low-Light Image Enhancement](https://mlsanity.com/paper/2412.07693/) (2024)
- [Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement](https://mlsanity.com/paper/2502.19867/) (2025)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision](https://mlsanity.com/paper/2309.06941/) (2023)
- [1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition](https://mlsanity.com/paper/2107.00818/) (2021)
- [Bounding-box deep calibration for high performance face detection](https://mlsanity.com/paper/2110.03892/) (2021)
- [RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images](https://mlsanity.com/paper/2201.02314/) (2022)
- [Toward Fast, Flexible, and Robust Low-Light Image Enhancement](https://mlsanity.com/paper/2204.10137/) (2022)
- [Improving the Detection of Small Oriented Objects in Aerial Images](https://mlsanity.com/paper/2401.06503/) (2024)
- [LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection](https://mlsanity.com/paper/2410.08810/) (2024)
- [Diffusion Models for Low-Light Image Enhancement: A Multi-Perspective Taxonomy and Performance Analysis](https://mlsanity.com/paper/2510.05976/) (2025)
- [TPCNet: Triple physical constraints for Low-light Image Enhancement](https://mlsanity.com/paper/2511.22052/) (2025)
- [Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform](https://mlsanity.com/paper/2607.24002/) (2026)

## Abstract (arXiv)

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/