VGGFace2: A dataset for recognising faces across pose and age

Cao, Qiong; Shen, Li; Xie, Weidi; Parkhi, Omkar M.; Zisserman, Andrew

doi:10.48550/arxiv.1710.08092

Cited by 37 publications

(46 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Amazons Rekognition Tool incorrectly matched the photos of 28 U.S. congressmen with the faces of criminals, especially the error rate was up to 39% for non-Caucasian people; according to [15], a year-long research investigation across A major driver of bias in face recognition, as well as other AI tasks, is the training data. Deep face recognition networks are often trained on large-scale training datasets, such as CASIA-WebFace [51], VGGFace2 [11] and MS-Celeb-1M [18], which are typically constructed by scraping websites like Google Images. Such data collecting methods can unintentionally produce data that encode gender, ethnic and culture biases.…”

Section: Introductionmentioning

confidence: 99%

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Wang¹,

Deng²

2019

Preprint

View full text Add to dashboard Cite

Racial equality is an important theme of international human rights law, but it has been largely obscured when the overall face recognition accuracy is pursued blindly. More facts indicate racial bias indeed degrades the fairness of recognition system and the error rates on non-Caucasians are usually much higher than Caucasians. To encourage fairness, we introduce the idea of adaptive margin to learn balanced performance for different races based on large margin losses. A reinforcement learning based race balance network (RL-RBN) is proposed. We formulate the process of finding the optimal margins for non-Caucasians as a Markov decision process and employ deep Q-learning to learn policies for an agent to select appropriate margin by approximating the Q-value function. Guided by the agent, the skewness of feature scatter between races can be reduced. Besides, we provide two ethnicity aware training datasets, called BUPT-Globalface and BUPT-Balancedface dataset, which can be utilized to study racial bias from both data and algorithm aspects. Extensive experiments on RFW database show that RL-RBN successfully mitigates racial bias and learns more balanced performance for different races.

show abstract

Section: Introductionmentioning

confidence: 99%

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Wang¹,

Deng²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In [7] authors use a CNN architecture (VGGNet)and achieve state-of-the-art accuracy (at the time of the writing) over FER2013 dataset by finetuning the parameters. Another similar CNN based approach was reported in [8] and evaluated the model with pre-trained face recognition models [9]. A more GAN related work was reported in [10] in which authors proposed a method which encodes the given image into feature space and then uses a Generalized Linear Model (GLM) to fit the general direction of different facial expressions in the feature space.…”

Section: Related Workmentioning

confidence: 99%

Explore the Expression: Facial Expression Generation using Auxiliary Classifier Generative Adversarial Network

Siddiqui¹

2022

Preprint

View full text Add to dashboard Cite

Facial expressions are a form of non-verbal communication that humans perform seamlessly for meaningful transfer of information. Most of the literature addresses the facial expression recognition aspect however, with the advent of Generative Models, it has become possible to explore the affect space in addition to mere classification of a set of expressions. In this article, we propose a generative model architecture which robustly generates a set of facial expressions for multiple character identities and explores the possibilities of generating complex expressions by combining the simple ones. .

show abstract

“…Our ability to preserve the identity of the source images is evaluated by computing the cosine similarity of the pretrained VGG-face network [5]. High values indicate preserved identity.…”

Section: Smile Glasses Beardmentioning

confidence: 99%

Mask Based Unsupervised Content Transfer

Mokady¹,

Benaim²,

Wolf³

et al. 2019

Preprint

View full text Add to dashboard Cite

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other. The proposed method disentangles the common and separate parts of these domains and, through the generation of a mask, focuses the attention of the underlying network to the desired augmentation alone, without wastefully reconstructing the entire target. This enables state-of-the-art quality and variety of content translation, as shown through extensive quantitative and qualitative evaluation. Furthermore, the novel mask-based formulation and regularization is accurate enough to achieve state-of-the-art performance in the realm of weakly supervised segmentation, where only class labels are given. To our knowledge, this is the first report that bridges the problems of domain disentanglement and weakly supervised segmentation. Our code is publicly available at https://github.com/rmokady/mbu-content-tansfer.Preprint. Under review.

show abstract

VGGFace2: A dataset for recognising faces across pose and age

Cited by 37 publications

References 17 publications

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Explore the Expression: Facial Expression Generation using Auxiliary Classifier Generative Adversarial Network

Mask Based Unsupervised Content Transfer

Contact Info

Product

Resources

About