Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation

@article{Qian2019AggregationVS,
  title={Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style Translation},
  author={Shengju Qian and Keqiang Sun and Wayne Wu and Chen Qian and Jiaya Jia},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={10152-10162}
}
Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied. In this paper, we investigate a new perspective of facial landmark detection and demonstrate it leads to further notable improvement. Given that any face images can be factored into space of style that captures lighting, texture and image environment, and a style-invariant structure space, our key idea is to leverage disentangled style and shape space of each individual to augment existing… Expand
Data Augmented Network for Facial Landmark Detection
TLDR
This paper proposes a multi-stage cascaded facial landmark detection, known as GLNet, to tradeoff between the model size and accuracy and demonstrates that this approach outperforms competing methods. Expand
Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal
TLDR
The FSMA framework is prominent in its versatility across a wide range of facial image applications and achieves state-of-the-art few-shot landmark detection performance and it offers satisfying solutions for few- shot face segmentation, stylization and facial shadow removal tasks for the first time. Expand
Structure-Coherent Deep Feature Learning for Robust Face Alignment
TLDR
This paper proposes a structure-coherent deep feature learning method for face alignment which leverages a landmark-graph relational network to enforce the structural relationships among landmarks and proposes a relative location loss to enhance the information of relative location of landmarks. Expand
LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment
  • Huilin Yang, Junyan Lyu, Pujin Cheng, Xiaoying Tang
  • Computer Science
  • ArXiv
  • 2021
TLDR
LDDMM-Face is comparable or superior to state-of-the-art methods for traditional within-dataset and same-annotation settings, but truly distinguishes itself with outstanding performance when dealing with weakly-supervised learning (partial-to-full), challenging cases, and different training and prediction datasets. Expand
Towards Unconstrained Facial Landmark Detection Robust to Diverse Cropping Manners
TLDR
A “Unconstrained Facial Landmark Detection” mechanism, that aims at enhancing the robustness of facial landmark detection, to deal with the inconsistent cropping manner issue and achieved above 6.5% improvement in standard normalized landmarks mean error reduction on face images cropped by diverse manners compared to baselines. Expand
When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model
TLDR
This work aims to explore a practical model that is accurate, robust, efficient, generalizable, and end-to-end trainable at the same time, and proposes two lightweight modules, namely dynamic query initialization (DQInit) and query-aware memory (QAMem). Expand
An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
TLDR
This work proposes an efficient multitask face alignment, face tracking and head pose estimation network (ATPN), which introduces a shortcut connection between shallow-layer features and deep- layer features to provide the structural information for face alignment and applies the CoordConv to the last few layers to provide coordinate information. Expand
Fast and Accurate: Structure Coherence Component for Face Alignment
TLDR
This paper presents a fast and accurate coordinate regression method for face alignment that leverages a dynamic sparse graph structure to passing features among the most related landmarks and proposes a novel objective function, named Soft Wing loss, to improve the accuracy. Expand
Pre-training strategies and datasets for facial representation learning
TLDR
This work introduces, for the first time, a comprehensive evaluation benchmark for facial representation learning consisting of 5 important face analysis tasks and systematically investigates two ways of large-scale representation learning applied to faces: supervised and unsupervised pre-training. Expand
ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets
TLDR
A novel Alternating Training Framework (ATF) is proposed, which leverages similarity and diversity across multi-media sources for a more robust detector and is feasible for both heatmap-based network and direct coordinate regression. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 97 REFERENCES
Style Aggregated Network for Facial Landmark Detection
TLDR
This work proposes a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection and demonstrates to perform well when compared with state-of-the-art algorithms on benchmark datasets AFLW and 300-W. Expand
Direct Shape Regression Networks for End-to-End Face Alignment
TLDR
DSRN efficiently constructs strong representations to disentangle highly nonlinear relationships between images and shapes; by incorporating a linear layer of low-rank learning, DSRN effectively encodes correlations of landmarks to improve performance. Expand
Learning Deep Representation for Face Alignment with Auxiliary Attributes
TLDR
A novel tasks-constrained deep model is formulated, which not only learns the inter-task correlation but also employs dynamic task coefficients to facilitate the optimization convergence when learning multiple complex tasks. Expand
Unconstrained Face Alignment via Cascaded Compositional Learning
TLDR
This work partitions the optimisation space into multiple domains of homogeneous descent, and predicts a shape as a composition of estimations from multiple domain-specific regressors to equip cascaded regressors with the capability to handle global shape variation and irregular appearance-shape relation in the unconstrained scenario. Expand
Pose-Invariant Face Alignment with a Single CNN
TLDR
A new layer, named visualization layer, is proposed, which can be integrated into the CNN architecture and enables joint optimization with different loss functions and demonstrates state-of-the-art accuracy, while reducing the training time by more than half compared to the typical cascade of CNNs. Expand
Joint Multi-View Face Alignment in the Wild
TLDR
This paper proposes the first, to the best of the knowledge, joint multi-view convolutional network to handle large pose variations across faces in-the-wild, and elegantly bridge face detection and facial landmark localization tasks. Expand
Convolutional aggregation of local evidence for large pose face alignment
TLDR
Convolutional Aggregation of Local Evidence (CALE) is proposed, a Convolutional Neural Network architecture particularly designed for addressing unconstrained face alignment and very large changes in shape and appearance typically encountered in animal faces. Expand
Disentangled Representation Learning GAN for Pose-Invariant Face Recognition
TLDR
Quantitative and qualitative evaluation on both controlled and in-the-wild databases demonstrate the superiority of DR-GAN over the state of the art. Expand
Face Alignment Across Large Poses: A 3D Solution
TLDR
3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN), is proposed, and a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling is proposed. Expand
Face detection, pose estimation, and landmark localization in the wild
TLDR
It is shown that tree-structured models are surprisingly effective at capturing global elastic deformation, while being easy to optimize unlike dense graph structures, in real-world, cluttered images. Expand
...
1
2
3
4
5
...