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
Proceedings ArticleDOI
ATF: Towards Robust Face Alignment via Leveraging Similarity and Diversity across Different Datasets
TL;DR: 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.
Posted Content
Facial Landmark Correlation Analysis.
Yongzhe Yan,Stefan Duffner,Priyanka Phutane,Anthony Berthelier,Christophe Blanc,Christophe Garcia,Thierry Chateau +6 more
TL;DR: By analyzing the landmark correlation, this work gains some interesting insights into the predictions of different landmark detection models (including random forests model and CNN models) and proposes a few-shot learning method that allows to considerably reduce the manual effort for dense landmark annotation.
Proceedings ArticleDOI
Face Alignment Using a GAN-based Photorealistic Synthetic Dataset
Haoqi Gao,Koichi Ogawara +1 more
TL;DR: This work aims to convert the synthetic face images generated by the Face generating middleware 3D model (FaceGen) into more realistic face images for training face alignment algorithms.
Journal ArticleDOI
A Facial Landmark Detection Method Based on Deep Knowledge Transfer
TL;DR: Wang et al. as mentioned in this paper proposed EfficientFAN, which adopts the encoder-decoder structure with a simple backbone EfficientNet-B0 as encoder and three upsampling layers and convolutional layers as decoder.
Proceedings ArticleDOI
Exaggerated Portrait Caricatures Generation Based On Seq2Seq
TL;DR: This paper achieves the extraction of facial structure features and explicit geometry features using sequence-to-sequence model and incorporates the matching threshold loss as a penalty term to constrain the exaggerated expression of 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.