# HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

arXiv: https://arxiv.org/abs/1603.01249 · HTML: https://mlsanity.com/paper/1603.01249/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2016.

## Built on by (most cited first, 30 of 104)

- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations](https://mlsanity.com/paper/2103.13843/) (2021)
- [Where in the World is this Image? Transformer-based Geo-localization in the Wild](https://mlsanity.com/paper/2204.13861/) (2022)
- [PIGEON: Predicting Image Geolocations](https://mlsanity.com/paper/2307.05845/) (2023)
- [Deep Learning for Micro-expression Recognition: A Survey](https://mlsanity.com/paper/2107.02823/) (2021)
- [Task Adaptive Parameter Sharing for Multi-Task Learning](https://mlsanity.com/paper/2203.16708/) (2022)
- [SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation](https://mlsanity.com/paper/2308.11509/) (2023)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Model Spider: Learning to Rank Pre-Trained Models Efficiently](https://mlsanity.com/paper/2306.03900/) (2023)
- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [Unsupervised Part Segmentation through Disentangling Appearance and Shape](https://mlsanity.com/paper/2105.12405/) (2021)
- [Pre-training strategies and datasets for facial representation learning](https://mlsanity.com/paper/2103.16554/) (2021)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation](https://mlsanity.com/paper/2309.07654/) (2023)
- [BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models](https://mlsanity.com/paper/2505.18132/) (2025)
- [Part-based Face Recognition with Vision Transformers](https://mlsanity.com/paper/2212.00057/) (2022)
- [Towards Accurate and Compact Architectures via Neural Architecture Transformer](https://mlsanity.com/paper/2102.10301/) (2021)
- [MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach](https://mlsanity.com/paper/2108.05060/) (2021)
- [AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning](https://mlsanity.com/paper/2110.13076/) (2021)
- [GazeOnce: Real-Time Multi-Person Gaze Estimation](https://mlsanity.com/paper/2204.09480/) (2022)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Graph-based Facial Affect Analysis: A Review](https://mlsanity.com/paper/2103.15599/) (2021)
- [DiSparse: Disentangled Sparsification for Multitask Model Compression](https://mlsanity.com/paper/2206.04662/) (2022)
- [Facial-Sketch Synthesis: A New Challenge](https://mlsanity.com/paper/2112.15439/) (2021)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Face-MLLM: A Large Face Perception Model](https://mlsanity.com/paper/2410.20717/) (2024)
- [On the representation and methodology for wide and short range head pose estimation](https://mlsanity.com/paper/2401.05807/) (2024)
- [ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation](https://mlsanity.com/paper/2103.00119/) (2021)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2311.01075/) (2023)

## Abstract (arXiv)

We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features. It exploits the synergy among the tasks which boosts up their individual performances. Additionally, we propose two variants of HyperFace: (1) HyperFace-ResNet that builds on the ResNet-101 model and achieves significant improvement in performance, and (2) Fast-HyperFace that uses a high recall fast face detector for generating region proposals to improve the speed of the algorithm. Extensive experiments show that the proposed models are able to capture both global and local information in faces and performs significantly better than many competitive algorithms for each of these four tasks.