Multi-Attention Network for 2D Face Alignment in the Wild

Most existing algorithms based on Convolutional Neural Networks (CNNs) for face alignment ignore the significance of attention mechanism. In this paper, we propose a Multi-Attention Network (MANet) for robust face alignment. Our attention mechanism includes multi-level feature attention and multi-scale attention. Multi-level feature attention is introduced for the purpose of paying attention to features of different levels, specifically, high-level feature attentions are essential for correlations among neighboring regions whereas low-level feature attentions focus on detailed description for local parts. While multi-scale attention is designed to obtain better representation the features of different scales. The attentions mentioned above are utilized for better feature presentation and information flow, thus our network is guided to emphasize the key information and suppress the less significant information. The experimental results on 300 W and WFLW datasets demonstrate the superiority of the proposed method over the state-of-the-art approaches.

[1]  Stefanos Zafeiriou,et al.  300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[2]  Shiguang Shan,et al.  Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment , 2014, ECCV.

[3]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[4]  Maja Pantic,et al.  Automatic Analysis of Facial Expressions: The State of the Art , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Linda G. Shapiro,et al.  ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation , 2018, ECCV.

[6]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Junping Du,et al.  Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaogang Wang,et al.  Multi-context Attention for Human Pose Estimation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yici Cai,et al.  Look at Boundary: A Boundary-Aware Face Alignment Algorithm , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Wenyan Wu,et al.  Leveraging Intra and Inter-Dataset Variations for Robust Face Alignment , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  George Trigeorgis,et al.  Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Pietro Perona,et al.  Robust Face Landmark Estimation under Occlusion , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[14]  David F. Salisbury.  Cognitive psychology and its implications for designing drill and practice programs for computers , 1990 .

[15]  Hanjiang Lai,et al.  Robust Facial Landmark Detection via Recurrent Attentive-Refinement Networks , 2016, ECCV.

[16]  Georgios Tzimiropoulos,et al.  How Far are We from Solving the 2D & 3D Face Alignment Problem? (and a Dataset of 230,000 3D Facial Landmarks) , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Yuxin Peng,et al.  Multi-attention Guided Activation Propagation in CNNs , 2018, PRCV.

[18]  Qingshan Liu,et al.  Stacked Hourglass Network for Robust Facial Landmark Localisation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Jian Sun,et al.  Face Alignment by Explicit Shape Regression , 2012, International Journal of Computer Vision.

[20]  Cheng Cheng,et al.  A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  José Miguel Buenaposada,et al.  A Deeply-Initialized Coarse-to-fine Ensemble of Regression Trees for Face Alignment , 2018, ECCV.

[22]  Jian Sun,et al.  Face Alignment at 3000 FPS via Regressing Local Binary Features , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Cheng Li,et al.  Face alignment by coarse-to-fine shape searching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Josef Kittler,et al.  Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.