ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation

@article{Fard2021ASMNetAL,
  title={ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation},
  author={Ali P. Fard and Hojjat Abdollahi and Mohammad H. Mahoor},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2021},
  pages={1521-1530}
}
Active Shape Model (ASM) is a statistical model of object shapes that represents a target structure. ASM can guide machine learning algorithms to fit a set of points representing an object (e.g., face) onto an image. This paper presents a lightweight Convolutional Neural Network (CNN) architecture with a loss function being assisted by ASM for face alignment and estimating head pose in the wild. We use ASM to first guide the network towards learning a smoother distribution of the facial… Expand

References

SHOWING 1-10 OF 65 REFERENCES
Look at Boundary: A Boundary-Aware Face Alignment Algorithm
TLDR
A novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation, which outperforms state-of-the-art methods by a large margin. Expand
MobileNetV2: Inverted Residuals and Linear Bottlenecks
TLDR
A new mobile architecture, MobileNetV2, is described that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes and allows decoupling of the input/output domains from the expressiveness of the transformation. Expand
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
TLDR
The proposed method, 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 to exploit the synergy among the tasks which boosts up their individual performances. Expand
Fine-Grained Head Pose Estimation Without Keypoints
TLDR
An elegant and robust way to determine pose is presented by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles directly from image intensities through joint binned pose classification and regression. Expand
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
TLDR
A new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs) is presented, and the superiority of the proposed method over the state-of-the-art approaches is proved. Expand
Leveraging Intra and Inter-Dataset Variations for Robust Face Alignment
  • Wenyan Wu, Shuo Yang
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2017
TLDR
A novel Deep Variation Leveraging Network (DVLN) is proposed, which consists of two strong coupling sub-networks, e.g., Dataset-Across Network (DA-Net) and Candidate-Decision Network (CD-Net), which takes advantage of different characteristics and distributions across different datasets, while CD-Net makes a final decision on candidate hypotheses given by DA-Net to leverage variations within one certain dataset. Expand
Face alignment by coarse-to-fine shape searching
TLDR
A novel face alignment framework based on coarse-to-fine shape searching that prevents the final solution from being trapped in local optima due to poor initialisation, and improves the robustness in coping with large pose variations. Expand
300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge
TLDR
The main goal of this challenge is to compare the performance of different methods on a new-collected dataset using the same evaluation protocol and the same mark-up and hence to develop the first standardized benchmark for facial landmark localization. Expand
Supervised Descent Method and Its Applications to Face Alignment
TLDR
A Supervised Descent Method (SDM) is proposed for minimizing a Non-linear Least Squares (NLS) function and achieves state-of-the-art performance in the problem of facial feature detection. Expand
Joint Head Pose Estimation and Face Alignment Framework Using Global and Local CNN Features
  • Xiang Xu, I. Kakadiaris
  • Computer Science
  • 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
  • 2017
TLDR
This paper explores the use of the global and local CNN features obtained from Convolutional Neural Networks for learning to estimate head pose and localize landmarks jointly and demonstrates that the algorithm, named JFA, improves both the head pose estimation and face alignment. Expand
...
1
2
3
4
5
...