Related papers: Addressing Bias in Face Detectors using Decentrali…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks. In this report, a novel approach for training state-of-the-art face detector is described. The key is to exploit the…

Deepfake detection models face two critical challenges: generalization to unseen manipulations and demographic fairness among population groups. However, existing approaches often demonstrate that these two objectives are inherently…

Addressing biases in AI models is crucial for ensuring fair and accurate predictions. However, obtaining large, unbiased datasets for training can be challenging. This paper proposes a comprehensive approach using multiple methods to remove…

Face alignment is a classic problem in the computer vision field. Previous works mostly focus on sparse alignment with a limited number of facial landmark points, i.e., facial landmark detection. In this paper, for the first time, we aim at…

This paper presents a novel deep learning-based approach for simultaneous age and gender classification from facial images, designed to enhance the effectiveness of targeted advertising campaigns. We propose a custom Convolutional Neural…

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. However, co-occurrence bias in the training dataset may hamper a DNN model's generalizability to unseen scenarios…

CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and…

We introduce our method and system for face recognition using multiple pose-aware deep learning models. In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate…

This paper presents Hierarchical Network Dissection, a general pipeline to interpret the internal representation of face-centric inference models. Using a probabilistic formulation, our pipeline pairs units of the model with concepts in our…

With the spread of DeepFake techniques, this technology has become quite accessible and good enough that there is concern about its malicious use. Faced with this problem, detecting forged faces is of utmost importance to ensure security…

The increasing prevalence of computer vision applications necessitates handling vast amounts of visual data, often containing personal information. While this technology offers significant benefits, it should not compromise privacy. Data…

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches,…

Face recognition in images is an active area of interest among the computer vision researchers. However, recognizing human face in an unconstrained environment, is a relatively less-explored area of research. Multiple face recognition in…

Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities.…

Deep learning approaches have achieved highly accurate face recognition by training the models with very large face image datasets. Unlike the availability of large 2D face image datasets, there is a lack of large 3D face datasets available…

The growing public concerns on data privacy in face recognition can be greatly addressed by the federated learning (FL) paradigm. However, conventional FL methods perform poorly due to the uniqueness of the task: broadcasting class centers…

Do very high accuracies of deep networks suggest pride of effective AI or are deep networks prejudiced? Do they suffer from in-group biases (own-race-bias and own-age-bias), and mimic the human behavior? Is in-group specific information…

Generic face detection algorithms do not perform very well in the mobile domain due to significant presence of occluded and partially visible faces. One promising technique to handle the challenge of partial faces is to design face…