Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample. Adversarial attacks that render DNNs vulnerable in real life represent a serious threat, given the consequences of improperly functioning autonomous vehicles, malware filters, or biometric authentication systems. In this paper, we apply Fast Gradient Sign Method to introduce perturbations to a facial image dataset and then test the output on a different classifier that we trained ourselves, to analyze transferability of this method. Next, we craft a variety of different attack algorithms on a facial image dataset, with the intention of developing untargeted black-box approaches assuming minimal adversarial knowledge, to further assess the robustness of DNNs in the facial recognition realm. We explore modifying single optimal pixels by a large amount, or modifying all pixels by a smaller amount, or combining these two attack approaches. While our single-pixel attacks achieved about a 15% average decrease in classifier confidence level for the actual class, the all-pixel attacks were more successful and achieved up to an 84% average decrease in confidence, along with an 81.6% misclassification rate, in the case of the attack that we tested with the highest levels of perturbation. Even with these high levels of perturbation, the face images remained fairly clearly identifiable to a human. We hope our research may help to advance the study of adversarial attacks on DNNs and defensive mechanisms to counteract them, particularly in the facial recognition domain.
As various databases of facial expressions have been made accessible over the last few decades, the Facial Expression Recognition (FER) task has gotten a lot of interest. The multiple sources of the available databases raised several challenges for facial recognition task. These challenges are usually addressed by Convolution Neural Network (CNN) architectures. Different from CNN models, a Transformer model based on attention mechanism has been presented recently to address vision tasks. One of the major issue with Transformers is the need of a large data for training, while most FER databases are limited compared to other vision applications. Therefore, we propose in this paper to learn a vision Transformer jointly with a Squeeze and Excitation (SE) block for FER task. The proposed method is evaluated on different publicly available FER databases including CK+, JAFFE,RAF-DB and SFEW. Experiments demonstrate that our model outperforms state-of-the-art methods on CK+ and SFEW and achieves competitive results on JAFFE and RAF-DB.
In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the release of sensitive information. This research focuses on the importance of face anonymization. Therefore, we introduce GANonymization, a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face which is synthesized into an anonymized version based on a generative adversarial network (GAN). The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face. Additionally, the performance of preserving facial expressions was evaluated on several affect recognition datasets and outperformed the state-of-the-art method in most categories. Finally, our approach was analyzed for its ability to remove various facial traits, such as jewelry, hair color, and multiple others. Here, it demonstrated reliable performance in removing these attributes. Our results suggest that GANonymization is a promising approach for anonymizing faces while preserving facial expressions.
Although face recognition has made impressive progress in recent years, we ignore the racial bias of the recognition system when we pursue a high level of accuracy. Previous work found that for different races, face recognition networks focus on different facial regions, and the sensitive regions of darker-skinned people are much smaller. Based on this discovery, we propose a new de-bias method based on gradient attention, called Gradient Attention Balance Network (GABN). Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning. This method mitigates the bias by making the network focus on similar facial regions. In addition, we also use masks to erase the Top-N sensitive facial regions, forcing the network to allocate its attention to a larger facial region. This method expands the sensitive region of darker-skinned people and further reduces the gap between GAM of darker-skinned people and GAM of Caucasians. Extensive experiments show that GABN successfully mitigates racial bias in face recognition and learns more balanced performance for people of different races.
Noisy label Facial Expression Recognition (FER) is more challenging than traditional noisy label classification tasks due to the inter-class similarity and the annotation ambiguity. Recent works mainly tackle this problem by filtering out large-loss samples. In this paper, we explore dealing with noisy labels from a new feature-learning perspective. We find that FER models remember noisy samples by focusing on a part of the features that can be considered related to the noisy labels instead of learning from the whole features that lead to the latent truth. Inspired by that, we propose a novel Erasing Attention Consistency (EAC) method to suppress the noisy samples during the training process automatically. Specifically, we first utilize the flip semantic consistency of facial images to design an imbalanced framework. We then randomly erase input images and use flip attention consistency to prevent the model from focusing on a part of the features. EAC significantly outperforms state-of-the-art noisy label FER methods and generalizes well to other tasks with a large number of classes like CIFAR100 and Tiny-ImageNet. The code is available at https://github.com/zyh-uaiaaaa/Erasing-Attention-Consistency.
Feature description is one of the most frequently studied areas in the expert systems and machine learning. Effective encoding of the images is an essential requirement for accurate matching. These encoding schemes play a significant role in recognition and retrieval systems. Facial recognition systems should be effective enough to accurately recognize individuals under intrinsic and extrinsic variations of the system. The templates or descriptors used in these systems encode spatial relationships of the pixels in the local neighbourhood of an image. Features encoded using these hand crafted descriptors should be robust against variations such as; illumination, background, poses, and expressions. In this paper a novel hand crafted cascaded asymmetric local pattern (CALP) is proposed for retrieval and recognition facial image. The proposed descriptor uniquely encodes relationship amongst the neighbouring pixels in horizontal and vertical directions. The proposed encoding scheme has optimum feature length and shows significant improvement in accuracy under environmental and physiological changes in a facial image. State of the art hand crafted descriptors namely; LBP, LDGP, CSLBP, SLBP and CSLTP are compared with the proposed descriptor on most challenging datasets namely; Caltech-face, LFW, and CASIA-face-v5. Result analysis shows that, the proposed descriptor outperforms state of the art under uncontrolled variations in expressions, background, pose and illumination.
In this paper, we present a multimodal \textit{and} dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the modalities from those that are specific to each modality. A static latent variable is also introduced to encode the information that is constant over time within an audiovisual speech sequence. The model is trained in an unsupervised manner on an audiovisual emotional speech dataset, in two stages. In the first stage, a vector quantized VAE (VQ-VAE) is learned independently for each modality, without temporal modeling. The second stage consists in learning the MDVAE model on the intermediate representation of the VQ-VAEs before quantization. The disentanglement between static versus dynamical and modality-specific versus modality-common information occurs during this second training stage. Extensive experiments are conducted to investigate how audiovisual speech latent factors are encoded in the latent space of MDVAE. These experiments include manipulating audiovisual speech, audiovisual facial image denoising, and audiovisual speech emotion recognition. The results show that MDVAE effectively combines the audio and visual information in its latent space. They also show that the learned static representation of audiovisual speech can be used for emotion recognition with few labeled data, and with better accuracy compared with unimodal baselines and a state-of-the-art supervised model based on an audiovisual transformer architecture.
The presence of bias in deep models leads to unfair outcomes for certain demographic subgroups. Research in bias focuses primarily on facial recognition and attribute prediction with scarce emphasis on face detection. Existing studies consider face detection as binary classification into 'face' and 'non-face' classes. In this work, we investigate possible bias in the domain of face detection through facial region localization which is currently unexplored. Since facial region localization is an essential task for all face recognition pipelines, it is imperative to analyze the presence of such bias in popular deep models. Most existing face detection datasets lack suitable annotation for such analysis. Therefore, we web-curate the Fair Face Localization with Attributes (F2LA) dataset and manually annotate more than 10 attributes per face, including facial localization information. Utilizing the extensive annotations from F2LA, an experimental setup is designed to study the performance of four pre-trained face detectors. We observe (i) a high disparity in detection accuracies across gender and skin-tone, and (ii) interplay of confounding factors beyond demography. The F2LA data and associated annotations can be accessed at http://iab-rubric.org/index.php/F2LA.
This paper presents a lightweight algorithm for feature extraction, classification of seven different emotions, and facial expression recognition in a real-time manner based on static images of the human face. In this regard, a Multi-Layer Perceptron (MLP) neural network is trained based on the foregoing algorithm. In order to classify human faces, first, some pre-processing is applied to the input image, which can localize and cut out faces from it. In the next step, a facial landmark detection library is used, which can detect the landmarks of each face. Then, the human face is split into upper and lower faces, which enables the extraction of the desired features from each part. In the proposed model, both geometric and texture-based feature types are taken into account. After the feature extraction phase, a normalized vector of features is created. A 3-layer MLP is trained using these feature vectors, leading to 96% accuracy on the test set.
This paper presents our Facial Action Units (AUs) recognition submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition.