Deep neural networks have proved hugely successful, achieving human-like performance on a variety of tasks. However, they are also computationally expensive, which has motivated the development of model compression techniques which reduce the resource consumption associated with deep learning models. Nevertheless, recent studies have suggested that model compression can have an adverse effect on algorithmic fairness, amplifying existing biases in machine learning models. With this project we aim to extend those studies to the context of facial expression recognition. To do that, we set up a neural network classifier to perform facial expression recognition and implement several model compression techniques on top of it. We then run experiments on two facial expression datasets, namely the Extended Cohn-Kanade Dataset (CK+DB) and the Real-World Affective Faces Database (RAF-DB), to examine the individual and combined effect that compression techniques have on the model size, accuracy and fairness. Our experimental results show that: (i) Compression and quantisation achieve significant reduction in model size with minimal impact on overall accuracy for both CK+DB and RAF-DB; (ii) in terms of model accuracy, the classifier trained and tested on RAF-DB seems more robust to compression compared to the CK+ DB; (iii) for RAF-DB, the different compression strategies do not seem to increase the gap in predictive performance across the sensitive attributes of gender, race and age which is in contrast with the results on the CK+DB, where compression seems to amplify existing biases for gender. We analyse the results and discuss the potential reasons for our findings.
Facial Expression Recognition (FER) in the wild is extremely challenging due to occlusions, variant head poses, face deformation and motion blur under unconstrained conditions. Although substantial progresses have been made in automatic FER in the past few decades, previous studies are mainly designed for lab-controlled FER. Real-world occlusions, variant head poses and other issues definitely increase the difficulty of FER on account of these information-deficient regions and complex backgrounds. Different from previous pure CNNs based methods, we argue that it is feasible and practical to translate facial images into sequences of visual words and perform expression recognition from a global perspective. Therefore, we propose Convolutional Visual Transformers to tackle FER in the wild by two main steps. First, we propose an attentional selective fusion (ASF) for leveraging the feature maps generated by two-branch CNNs. The ASF captures discriminative information by fusing multiple features with global-local attention. The fused feature maps are then flattened and projected into sequences of visual words. Second, inspired by the success of Transformers in natural language processing, we propose to model relationships between these visual words with global self-attention. The proposed method are evaluated on three public in-the-wild facial expression datasets (RAF-DB, FERPlus and AffectNet). Under the same settings, extensive experiments demonstrate that our method shows superior performance over other methods, setting new state of the art on RAF-DB with 88.14%, FERPlus with 88.81% and AffectNet with 61.85%. We also conduct cross-dataset evaluation on CK+ show the generalization capability of the proposed method.
Emotions play a central role in the social life of every human being, and their study, which represents a multidisciplinary subject, embraces a great variety of research fields. Especially concerning the latter, the analysis of facial expressions represents a very active research area due to its relevance to human-computer interaction applications. In such a context, Facial Expression Recognition (FER) is the task of recognizing expressions on human faces. Typically, face images are acquired by cameras that have, by nature, different characteristics, such as the output resolution. It has been already shown in the literature that Deep Learning models applied to face recognition experience a degradation in their performance when tested against multi-resolution scenarios. Since the FER task involves analyzing face images that can be acquired with heterogeneous sources, thus involving images with different quality, it is plausible to expect that resolution plays an important role in such a case too. Stemming from such a hypothesis, we prove the benefits of multi-resolution training for models tasked with recognizing facial expressions. Hence, we propose a two-step learning procedure, named MAFER, to train DCNNs to empower them to generate robust predictions across a wide range of resolutions. A relevant feature of MAFER is that it is task-agnostic, i.e., it can be used complementarily to other objective-related techniques. To assess the effectiveness of the proposed approach, we performed an extensive experimental campaign on publicly available datasets: \fer{}, \raf{}, and \oulu{}. For a multi-resolution context, we observe that with our approach, learning models improve upon the current SotA while reporting comparable results in fix-resolution contexts. Finally, we analyze the performance of our models and observe the higher discrimination power of deep features generated from them.
In this paper, we examine the multi-task training of lightweight convolutional neural networks for face identification and classification of facial attributes (age, gender, ethnicity) trained on cropped faces without margins. It is shown that it is still necessary to fine-tune these networks in order to predict facial expressions. Several models are presented based on MobileNet, EfficientNet and RexNet architectures. It was experimentally demonstrated that our models are characterized by the state-of-the-art emotion classification accuracy on AffectNet dataset and near state-of-the-art results in age, gender and race recognition for UTKFace dataset. Moreover, it is shown that the usage of our neural network as a feature extractor of facial regions in video frames and concatenation of several statistical functions (mean, max, etc.) leads to 4.5\% higher accuracy than the previously known state-of-the-art single models for AFEW and VGAF datasets from the EmotiW challenges. The models and source code are publicly available at https://github.com/HSE-asavchenko/face-emotion-recognition.
Automated Facial Expression Recognition (FER) has remained a challenging and interesting problem. Despite efforts made in developing various methods for FER, existing approaches traditionally lack generalizability when applied to unseen images or those that are captured in wild setting. Most of the existing approaches are based on engineered features (e.g. HOG, LBPH, and Gabor) where the classifier's hyperparameters are tuned to give best recognition accuracies across a single database, or a small collection of similar databases. Nevertheless, the results are not significant when they are applied to novel data. This paper proposes a deep neural network architecture to address the FER problem across multiple well-known standard face datasets. Specifically, our network consists of two convolutional layers each followed by max pooling and then four Inception layers. The network is a single component architecture that takes registered facial images as the input and classifies them into either of the six basic or the neutral expressions. We conducted comprehensive experiments on seven publically available facial expression databases, viz. MultiPIE, MMI, CK+, DISFA, FERA, SFEW, and FER2013. The results of proposed architecture are comparable to or better than the state-of-the-art methods and better than traditional convolutional neural networks and in both accuracy and training time.
Face identification/recognition has significantly advanced over the past years. However, most of the proposed approaches rely on static RGB frames and on neutral facial expressions. This has two disadvantages. First, important facial shape cues are ignored. Second, facial deformations due to expressions can have an impact on the performance of such a method. In this paper, we propose a novel framework for dynamic 3D face identification/recognition based on facial keypoints. Each dynamic sequence of facial expressions is represented as a spatio-temporal graph, which is constructed using 3D facial landmarks. Each graph node contains local shape and texture features that are extracted from its neighborhood. For the classification/identification of faces, a Spatio-temporal Graph Convolutional Network (ST-GCN) is used. Finally, we evaluate our approach on a challenging dynamic 3D facial expression dataset.
For a number of tasks solved using deep learning techniques, an exogenous variable can be identified such that (a) it heavily influences the appearance of the different classes, and (b) an ideal classifier should be invariant to this variable. An example of such exogenous variable is identity if facial expression recognition (FER) is considered. In this paper, we propose a dual exogenous/endogenous representation. The former captures the exogenous variable whereas the second one models the task at hand (e.g. facial expression). We design a prediction layer that uses a deep ensemble conditioned by the exogenous representation. It employs a differential tree gate that learns an adaptive weak predictor weighting, therefore modeling a partition of the exogenous representation space, upon which the weak predictors specialize. This layer explicitly models the dependency between the exogenous variable and the predicted task (a). We also propose an exogenous dispelling loss to remove the exogenous information from the endogenous representation, enforcing (b). Thus, the exogenous information is used two times in a throwable fashion, first as a conditioning variable for the target task, and second to create invariance within the endogenous representation. We call this method THIN, standing for THrowable Information Networks. We experimentally validate THIN in several contexts where an exogenous information can be identified, such as digit recognition under large rotations and shape recognition at multiple scales. We also apply it to FER with identity as the exogenous variable. In particular, we demonstrate that THIN significantly outperforms state-of-the-art approaches on several challenging datasets.
Faces manifest large variations in many aspects, such as identity, expression, pose, and face styling. Therefore, it is a great challenge to disentangle and extract these characteristics from facial images, especially in an unsupervised manner. In this work, we introduce cycle-consistency in facial characteristics as free supervisory signal to learn facial representations from unlabeled facial images. The learning is realized by superimposing the facial motion cycle-consistency and identity cycle-consistency constraints. The main idea of the facial motion cycle-consistency is that, given a face with expression, we can perform de-expression to a neutral face via the removal of facial motion and further perform re-expression to reconstruct back to the original face. The main idea of the identity cycle-consistency is to exploit both de-identity into mean face by depriving the given neutral face of its identity via feature re-normalization and re-identity into neutral face by adding the personal attributes to the mean face. At training time, our model learns to disentangle two distinct facial representations to be useful for performing cycle-consistent face reconstruction. At test time, we use the linear protocol scheme for evaluating facial representations on various tasks, including facial expression recognition and head pose regression. We also can directly apply the learnt facial representations to person recognition, frontalization and image-to-image translation. Our experiments show that the results of our approach is competitive with those of existing methods, demonstrating the rich and unique information embedded in the disentangled representations. Code is available at https://github.com/JiaRenChang/FaceCycle .
Compared with facial emotion recognition on categorical model, the dimensional emotion recognition can describe numerous emotions of the real world more accurately. Most prior works of dimensional emotion estimation only considered laboratory data and used video, speech or other multi-modal features. The effect of these methods applied on static images in the real world is unknown. In this paper, a two-level attention with two-stage multi-task learning (2Att-2Mt) framework is proposed for facial emotion estimation on only static images. Firstly, the features of corresponding region(position-level features) are extracted and enhanced automatically by first-level attention mechanism. In the following, we utilize Bi-directional Recurrent Neural Network(Bi-RNN) with self-attention(second-level attention) to make full use of the relationship features of different layers(layer-level features) adaptively. Owing to the inherent complexity of dimensional emotion recognition, we propose a two-stage multi-task learning structure to exploited categorical representations to ameliorate the dimensional representations and estimate valence and arousal simultaneously in view of the correlation of the two targets. The quantitative results conducted on AffectNet dataset show significant advancement on Concordance Correlation Coefficient(CCC) and Root Mean Square Error(RMSE), illustrating the superiority of the proposed framework. Besides, extensive comparative experiments have also fully demonstrated the effectiveness of different components.
Deep models have achieved impressive performance for face hallucination tasks. However, we observe that directly feeding the hallucinated facial images into recog- nition models can even degrade the recognition performance despite the much better visualization quality. In this paper, we address this problem by jointly learning a deep model for two tasks, i.e. face hallucination and recognition. In particular, we design an end-to-end deep convolution network with hallucination sub-network cascaded by recognition sub-network. The recognition sub- network are responsible for producing discriminative feature representations using the hallucinated images as inputs generated by hallucination sub-network. During training, we feed LR facial images into the network and optimize the parameters by minimizing two loss items, i.e. 1) face hallucination loss measured by the pixel wise difference between the ground truth HR images and network-generated images; and 2) verification loss which is measured by the classification error and intra-class distance. We extensively evaluate our method on LFW and YTF datasets. The experimental results show that our method can achieve recognition accuracy 97.95% on 4x down-sampled LFW testing set, outperforming the accuracy 96.35% of conventional face recognition model. And on the more challenging YTF dataset, we achieve recognition accuracy 90.65%, a margin over the recognition accuracy 89.45% obtained by conventional face recognition model on the 4x down-sampled version.
Add to Chrome
Add to Firefox