Head pose estimation and face alignment constitute a backbone preprocessing for many applications relying on face analysis. While both are closely related tasks, they are generally addressed separately, e.g. by deducing the head pose from the landmark locations. In this paper, we propose to entwine face alignment and head pose tasks inside an attentional cascade. This cascade uses a geometry transfer network for integrating heterogeneous annotations to enhance landmark localization accuracy. Furthermore, we propose a doubly-conditional fusion scheme to select relevant feature maps, and regions thereof, based on a current head pose and landmark localization estimate. We empirically show the benefit of entwining head pose and landmark localization objectives inside our architecture, and that the proposed AC-DC model enhances the state-of-the-art accuracy on multiple databases for both face alignment and head pose estimation tasks.
This paper addresses the problem of analysing the performance of 3D face alignment (3DFA), or facial landmark localization. This task is usually supervised, based on annotated datasets. Nevertheless, in the particular case of 3DFA, the annotation process is rarely error-free, which strongly biases the results. Alternatively, unsupervised performance analysis (UPA) is investigated. The core ingredient of the proposed methodology is the robust estimation of the rigid transformation between predicted landmarks and model landmarks. It is shown that the rigid mapping thus computed is affected neither by non-rigid facial deformations, due to variabilities in expression and in identity, nor by landmark localization errors, due to various perturbations. The guiding idea is to apply the estimated rotation, translation and scale to a set of predicted landmarks in order to map them onto a mathematical home for the shape embedded in these landmarks (including possible errors). UPA proceeds as follows: (i) 3D landmarks are extracted from a 2D face using the 3DFA method under investigation; (ii) these landmarks are rigidly mapped onto a canonical (frontal) pose, and (iii) a statistically-robust confidence score is computed for each landmark. This allows to assess whether the mapped landmarks lie inside (inliers) or outside (outliers) a confidence volume. An experimental evaluation protocol, that uses publicly available datasets and several 3DFA software packages associated with published articles, is described in detail. The results show that the proposed analysis is consistent with supervised metrics and that it can be used to measure the accuracy of both predicted landmarks and of automatically annotated 3DFA datasets, to detect errors and to eliminate them. Source code and supplemental materials for this paper are publicly available at https://team.inria.fr/robotlearn/upa3dfa/.
Modern face alignment methods have become quite accurate at predicting the locations of facial landmarks, but they do not typically estimate the uncertainty of their predicted locations nor predict whether landmarks are visible. In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities. We model these as mixed random variables and estimate them using a deep network trained with our proposed Location, Uncertainty, and Visibility Likelihood (LUVLi) loss. In addition, we release an entirely new labeling of a large face alignment dataset with over 19,000 face images in a full range of head poses. Each face is manually labeled with the ground-truth locations of 68 landmarks, with the additional information of whether each landmark is unoccluded, self-occluded (due to extreme head poses), or externally occluded. Not only does our joint estimation yield accurate estimates of the uncertainty of predicted landmark locations, but it also yields state-of-the-art estimates for the landmark locations themselves on multiple standard face alignment datasets. Our method's estimates of the uncertainty of predicted landmark locations could be used to automatically identify input images on which face alignment fails, which can be critical for downstream tasks.
Although heatmap regression is considered a state-of-the-art method to locate facial landmarks, it suffers from huge spatial complexity and is prone to quantization error. To address this, we propose a novel attentive one-dimensional heatmap regression method for facial landmark localization. First, we predict two groups of 1D heatmaps to represent the marginal distributions of the x and y coordinates. These 1D heatmaps reduce spatial complexity significantly compared to current heatmap regression methods, which use 2D heatmaps to represent the joint distributions of x and y coordinates. With much lower spatial complexity, the proposed method can output high-resolution 1D heatmaps despite limited GPU memory, significantly alleviating the quantization error. Second, a co-attention mechanism is adopted to model the inherent spatial patterns existing in x and y coordinates, and therefore the joint distributions on the x and y axes are also captured. Third, based on the 1D heatmap structures, we propose a facial landmark detector capturing spatial patterns for landmark detection on an image; and a tracker further capturing temporal patterns with a temporal refinement mechanism for landmark tracking. Experimental results on four benchmark databases demonstrate the superiority of our method.
Face alignment is crucial for face recognition and has been widely adopted. However, current practice is too simple and under-explored. There lacks an understanding of how important face alignment is and how it should be performed, for recognition. This work studies these problems and makes two contributions. First, it provides an in-depth and quantitative study of how alignment strength affects recognition accuracy. Our results show that excessive alignment is harmful and an optimal balanced point of alignment is in need. To strike the balance, our second contribution is a novel joint learning approach where alignment learning is controllable with respect to its strength and driven by recognition. Our proposed method is validated by comprehensive experiments on several benchmarks, especially the challenging ones with large pose.
Facial action unit (AU) detection and face alignment are two highly correlated tasks, since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. However, most existing AU detection works handle the two tasks independently by treating face alignment as a preprocessing, and often use landmarks to predefine a fixed region or attention for each AU. In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before. In particular, multi-scale shared feature is learned firstly, and high-level feature of face alignment is fed into AU detection. Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively. Finally, the assembled local features are integrated with face alignment feature and global feature for AU detection. Extensive experiments demonstrate that our framework (i) significantly outperforms the state-of-the-art AU detection methods on the challenging BP4D, DISFA, GFT and BP4D+ benchmarks, (ii) can adaptively capture the irregular region of each AU, (iii) achieves competitive performance for face alignment, and (iv) also works well under partial occlusions and non-frontal poses. The code for our method is available at https://github.com/ZhiwenShao/PyTorch-JAANet.
Recently, heatmap regression models have become popular due to their superior performance in locating facial landmarks. However, three major problems still exist among these models: (1) they are computationally expensive; (2) they usually lack explicit constraints on global shapes; (3) domain gaps are commonly present. To address these problems, we propose Pixel-in-Pixel Net (PIPNet) for facial landmark detection. The proposed model is equipped with a novel detection head based on heatmap regression, which conducts score and offset predictions simultaneously on low-resolution feature maps. By doing so, repeated upsampling layers are no longer necessary, enabling the inference time to be largely reduced without sacrificing model accuracy. Besides, a simple but effective neighbor regression module is proposed to enforce local constraints by fusing predictions from neighboring landmarks, which enhances the robustness of the new detection head. To further improve the cross-domain generalization capability of PIPNet, we propose self-training with curriculum. This training strategy is able to mine more reliable pseudo-labels from unlabeled data across domains by starting with an easier task, then gradually increasing the difficulty to provide more precise labels. Extensive experiments demonstrate the superiority of PIPNet, which obtains state-of-the-art results on three out of six popular benchmarks under the supervised setting. The results on two cross-domain test sets are also consistently improved compared to the baselines. Notably, our lightweight version of PIPNet runs at 35.7 FPS and 200 FPS on CPU and GPU, respectively, while still maintaining a competitive accuracy to state-of-the-art methods. The code of PIPNet is available at https://github.com/jhb86253817/PIPNet.
Human affect recognition is an essential part of natural human-computer interaction. However, current methods are still in their infancy, especially for in-the-wild data. In this work, we introduce our submission to the Affective Behavior Analysis in-the-wild (ABAW) 2020 competition. We propose a two-stream aural-visual analysis model to recognize affective behavior from videos. Audio and image streams are first processed separately and fed into a convolutional neural network. Instead of applying recurrent architectures for temporal analysis we only use temporal convolutions. Furthermore, the model is given access to additional features extracted during face-alignment. At training time, we exploit correlations between different emotion representations to improve performance. Our model achieves promising results on the challenging Aff-Wild2 database.
An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods.
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos. Unlike existing fully supervised methods which rely on numerous annotations by hand, our learner exploits large scale unlabeled videos plus available labeled data to generate auxiliary plausible training annotations. Motivated by the fact that neighbouring facial landmarks are usually correlated and coherent across consecutive frames, our approach automatically reasons about discriminative spatial-temporal relationships among landmarks for stable face tracking. Specifically, we carefully develop an interpretable and efficient network module, which disentangles facial geometry relationship for every static frame and simultaneously enforces the bi-directional cycle-consistency across adjacent frames, thus allowing the modeling of intrinsic spatial-temporal relations from raw face sequences. Extensive experimental results demonstrate that our approach surpasses the performance of most fully supervised state-of-the-arts.
Accurate face detection and facial landmark localization are crucial to any face recognition system. We present a series of three single-stage RCNNs with different sized backbones (MobileNetV2-25, MobileNetV2-100, and ResNet101) and a six-layer feature pyramid trained exclusively on the WIDER FACE dataset. We compare the face detection and landmark accuracies using eight context module architectures, four proposed by previous research and four modified versions. We find no evidence that any of the proposed architectures significantly overperform and postulate that the random initialization of the additional layers is at least of equal importance. To show this we present a model that achieves near state-of-the-art performance on WIDER FACE and also provides high accuracy landmarks with a simple context module. We also present results using MobileNetV2 backbones, which achieve over 90% average precision on the WIDER FACE hard validation set while being able to run in real-time. By comparing to other authors, we show that our models exceed the state-of-the-art for similar-sized RCNNs and match the performance of much heavier networks.
Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters. We introduce a semi-supervised method in which the crucial idea is to first generate implicit face knowledge from the large amounts of unlabeled images of faces available today. In a first, completely unsupervised stage, we train an adversarial autoencoder to reconstruct faces via a low-dimensional face embedding. In a second, supervised stage, we interleave the decoder with transfer layers to retask the generation of color images to the prediction of landmark heatmaps. Our framework (3FabRec) achieves state-of-the-art performance on several common benchmarks and, most importantly, is able to maintain impressive accuracy on extremely small training sets down to as few as 10 images. As the interleaved layers only add a low amount of parameters to the decoder, inference runs at several hundred FPS on a GPU.
This inherent relations among multiple face analysis tasks, such as landmark detection, head pose estimation, gender recognition and face attribute estimation are crucial to boost the performance of each task, but have not been thoroughly explored since typically these multiple face analysis tasks are handled as separate tasks. In this paper, we propose a novel deep multi-task adversarial learning method to localize facial landmark, estimate head pose and recognize gender jointly or estimate multiple face attributes simultaneously through exploring their dependencies from both image representation-level and label-level. Specifically, the proposed method consists of a deep recognition network R and a discriminator D. The deep recognition network is used to learn the shared middle-level image representation and conducts multiple face analysis tasks simultaneously. Through multi-task learning mechanism, the recognition network explores the dependencies among multiple face analysis tasks, such as facial landmark localization, head pose estimation, gender recognition and face attribute estimation from image representation-level. The discriminator is introduced to enforce the distribution of the multiple face analysis tasks to converge to that inherent in the ground-truth labels. During training, the recognizer tries to confuse the discriminator, while the discriminator competes with the recognizer through distinguishing the predicted label combination from the ground-truth one. Though adversarial learning, we explore the dependencies among multiple face analysis tasks from label-level. Experimental results on four benchmark databases, i.e., the AFLW database, the Multi-PIE database, the CelebA database and the LFWA database, demonstrate the effectiveness of the proposed method for multiple face analyses.
With the growth of popularity of facial micro-expressions in recent years, the demand for long videos with micro- and macro-expressions remains high. Extended from SAMM, a micro-expressions dataset released in 2016, this paper presents SAMM Long Videos dataset for spontaneous micro- and macro-expressions recognition and spotting. SAMM Long Videos dataset consists of 147 long videos with 343 macro-expressions and 159 micro-expressions. The dataset is FACS-coded with detailed Action Units (AUs). We compare our dataset with Chinese Academy of Sciences Macro-Expressions and Micro-Expressions (CAS(ME)2) dataset, which is the only available fully annotated dataset with micro- and macro-expressions. Furthermore, we preprocess the long videos using OpenFace, which includes face alignment and detection of facial AUs. We conduct facial expression spotting using this dataset and compare it with the baseline of MEGC III. Our spotting method outperformed the baseline result with F1-score of 0.3299.
Deep learning has become popular in recent years primarily due to the powerful computing device such as GPUs. However, deploying these deep models to end-user devices, smart phones, or embedded systems with limited resources is challenging. To reduce the computation and memory costs, we propose a novel lightweight deep learning module by low-rank pointwise residual (LPR) convolution, called LPRNet. Essentially, LPR aims at using low-rank approximation in pointwise convolution to further reduce the module size, while keeping depthwise convolutions as the residual module to rectify the LPR module. This is critical when the low-rankness undermines the convolution process. We embody our design by replacing modules of identical input-output dimension in MobileNet and ShuffleNetv2. Experiments on visual recognition tasks including image classification and face alignment on popular benchmarks show that our LPRNet achieves competitive performance but with significant reduction of Flops and memory cost compared to the state-of-the-art deep models focusing on model compression.
There is an urgent need to apply face alignment in a memory-efficient and real-time manner due to the recent explosion of face recognition applications. However, impact factors such as large pose variation and computational inefficiency, still hinder its broad implementation. To this end, we propose a computationally efficient deep evolutionary model integrated with 3D Diffusion Heap Maps (DHM). First, we introduce a sparse 3D DHM to assist the initial modeling process under extreme pose conditions. Afterward, a simple and effective CNN feature is extracted and fed to Recurrent Neural Network (RNN) for evolutionary learning. To accelerate the model, we propose an efficient network structure to accelerate the evolutionary learning process through a factorization strategy. Extensive experiments on three popular alignment databases demonstrate the advantage of the proposed models over the state-of-the-art, especially under large-pose conditions. Notably, the computational speed of our model is 6 times faster than the state-of-the-art on CPU and 14 times on GPU. We also discuss and analyze the limitations of our models and future research work.
In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-toimage translation network to predict a displacement map in UVspace. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of the proposed method over previous work.
Importance: Machine learning (ML) approaches to facial landmark localization carry great clinical potential for quantitative assessment of facial function as they enable high-throughput automated quantification of relevant facial metrics from photographs. However, translation from research settings to clinical applications requires important improvements. Objective: To develop an ML algorithm for accurate facial landmarks localization in photographs of facial palsy patients, and use it as part of an automated computer-aided diagnosis system. Design, Setting, and Participants: Facial landmarks were manually localized in portrait photographs of eight expressions obtained from 200 facial palsy patients and 10 controls. A novel ML model for automated facial landmark localization was trained using this disease-specific database. Model output was compared to manual annotations and the output of a model trained using a larger database consisting only of healthy subjects. Model accuracy was evaluated by the normalized root mean square error (NRMSE) between algorithms' prediction and manual annotations. Results: Publicly available algorithms provide poor results when applied to patients compared to healthy controls (NRMSE, 8.56 +/- 2.16 vs. 7.09 +/- 2.34, p << 0.01). We found significant improvement in facial landmark localization accuracy for the clinical population when using a model trained with a relatively small number patients' photographs (1440) compared to a model trained using several thousand more images of healthy faces (NRMSE, 6.03 +/- 2.43 vs. 8.56 +/- 2.16, p << 0.01). Conclusions: Retraining a landmark detection model with a small number of clinical images significantly improved landmark detection performance in frontal view photographs of the clinical population. These results represent the first steps towards an automatic system for computer-aided assessment in facial palsy.
Face alignment consists of aligning a shape model on a face image. It is an active domain in computer vision as it is a preprocessing for a number of face analysis and synthesis applications. Current state-of-the-art methods already perform well on "easy" datasets, with moderate head pose variations, but may not be robust for "in-the-wild" data with poses up to 90{\deg}. In order to increase robustness to an ensemble of factors of variations (e.g. head pose or occlusions), a given layer (e.g. a regressor or an upstream CNN layer) can be replaced by a Mixture of Experts (MoE) layer that uses an ensemble of experts instead of a single one. The weights of this mixture can be learned as gating functions to jointly learn the experts and the corresponding weights. In this paper, we propose to use tree-structured gates which allows a hierarchical weighting of the experts (Tree-MoE). We investigate the use of Tree-MoE layers in different contexts in the frame of face alignment with cascaded regression, firstly for emphasizing relevant, more specialized feature extractors depending of a high-level semantic information such as head pose (Pose-Tree-MoE), and secondly as an overall more robust regression layer. We perform extensive experiments on several challenging face alignment datasets, demonstrating that our approach outperforms the state-of-the-art methods.
This paper studies the problem of aligning a set of face images of the same individual into a normalized image while removing the outliers like partial occlusion, extreme facial expression as well as significant illumination variation. Our model seeks an optimal image domain transformation such that the matrix of misaligned images can be decomposed as the sum of a sparse matrix of noise and a rank-one matrix of aligned images. The image transformation is learned in an unsupervised manner, which means that ground-truth aligned images are unnecessary for our model. Specifically, we make use of the remarkable non-linear transforming ability of generative adversarial network(GAN) and guide it with low-rank generation as well as sparse noise constraint to achieve the face alignment. We verify the efficacy of the proposed model with extensive experiments on real-world face databases, demonstrating higher accuracy and efficiency than existing methods.