Deep Alignment Network: A Convolutional Neural Network for Robust Face Alignment
Marek Kowalski,Jacek Naruniec,Tomasz Trzcinski +2 more
- pp 2034-2043
Reads0
Chats0
TLDR
The use of entire face images rather than patches allows DAN to handle face images with large variation in head pose and difficult initializations, and reduces the state-of-the-art failure rate by up to 70%.Abstract:
In this paper, we propose Deep Alignment Network (DAN), a robust face alignment method based on a deep neural network architecture. DAN consists of multiple stages, where each stage improves the locations of the facial landmarks estimated by the previous stage. Our method uses entire face images at all stages, contrary to the recently proposed face alignment methods that rely on local patches. This is possible thanks to the use of landmark heatmaps which provide visual information about landmark locations estimated at the previous stages of the algorithm. The use of entire face images rather than patches allows DAN to handle face images with large variation in head pose and difficult initializations. An extensive evaluation on two publicly available datasets shows that DAN reduces the state-of-the-art failure rate by up to 70%. Our method has also been submitted for evaluation as part of the Menpo challenge.read more
Citations
More filters
Journal ArticleDOI
Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
TL;DR: In this article, a structure-aware fully convolutional network is proposed to implicitly take priors about the structure of pose components into account during training of the deep network, which significantly outperforms several state-of-the-art methods and almost always generates plausible pose predictions.
Posted Content
DeCaFA: Deep Convolutional Cascade for Face Alignment In The Wild.
TL;DR: DeCaFA as discussed by the authors is an end-to-end deep convolutional cascade architecture for face alignment, which uses fully-convolutional stages to keep full spatial resolution throughout the cascade and uses multiple chained transfer layers with spatial softmax to produce landmark-wise attention maps for each of several landmark alignment tasks.
Posted Content
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
Xinyao Wang,Liefeng Bo,Li Fuxin +2 more
TL;DR: Wang et al. as mentioned in this paper proposed a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels, which penalizes loss more on foreground pixels while less on background pixels.
Proceedings ArticleDOI
Multi-angle Head Pose Classification when Wearing the Mask for Face Recognition under the COVID-19 Coronavirus Epidemic
TL;DR: A method HGL to deal with the head pose classification by adopting color texture analysis of images and line portrait is established, and compared with the algorithms based on facial landmark detection and convolutional neural network, the proposed method has achieved a better performance.
Proceedings ArticleDOI
I Know How You Feel: Emotion Recognition with Facial Landmarks
TL;DR: This work postulates a fundamentally different approach to solve emotion recognition task that relies on incorporating facial landmarks as a part of the classification loss function, and extends a recently proposed Deep Alignment Network, that achieves state-of-the-art results in the recent facial landmark recognition challenge, with a term related to facial features.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.