Fetching the paper…
Reading the bibliography…
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 being encoded sub-consciously by the deep networks? This research attempts to answer these questions and presents an in-depth analysis of `bias' in deep learning based face recognition systems.
Descriptions of white and black faces by white and black subjects
H. D. Ellis, J. B. Deregowski, and J. W. Shepherd · 1975
Earlier work this paper cites.
Thirty years of investigating the own-race bias in memory for faces: A meta-analytic review
C. Meissner and J. Brigham · 2001
Earlier work this paper cites.
Thirty years of investigating the own-race bias in memory for faces: A meta-analytic review
C. A. Meissner and J. C. Brigham · 2001
Earlier work this paper cites.
An own-age bias in face recognition for children and older adults
J. S. Anastasi and M. G. Rhodes · 2005
Earlier work this paper cites.
Reducing the own-race bias in face recognition by shifting attention
P. J. Hills and M. B. Lewis · 2006
Earlier work this paper cites.
Face recognition by humans: Nineteen results all computer vision researchers should know about
P. Sinha, B. Balas, Y. Ostrovsky, and R. Russell · 2006
Earlier work this paper cites.
Visualizing data using t-sne
L. v. d. Maaten and G. Hinton · 2008
Earlier work this paper cites.
Perceptual other-race training reduces implicit racial bias
S. Lebrecht, L. J. Pierce, M. J. Tarr, and J. W. Tanaka · 2009
Earlier work this paper cites.
MORPH: Development and optimization of a longitudinal age progression database
A. W. Rawls and K. Ricanek · 2009
Earlier work this paper cites.
Multi-pie
R. Gross, I. Matthews, J. Cohn, T. Kanade, and S. Baker · 2010
Earlier work this paper cites.
Ageing faces in ageing minds: a review on the own-age bias in face recognition
H. Wiese, J. Komes, and S. R. Schweinberger · 2013
Earlier work this paper cites.
Age and gender estimation of unfiltered faces
E. Eidinger, R. Enbar, and T. Hassner · 2014
Earlier work this paper cites.
Learning race from face: A survey
S. Fu, H. He, and Z.-G. Hou · 2014
Cited alongside, same era.
Face recognition and retrieval using cross-age reference coding with cross-age celebrity dataset
B. Chen, C. Chen, and W. H. Hsu · 2015
Cited alongside, same era.
DEX: Deep expectation of apparent age from a single image
R. Rothe, R. Timofte, and L. V. Gool · 2015
Cited alongside, same era.
Man is to computer programmer as woman is to homemaker? debiasing word embeddings
T. Bolukbasi, K.-W. Chang, J. Zou, V. Saligrama, and A. Kalai · 2016
Cited alongside, same era.
MS-Celeb-1M: A dataset and benchmark for large-scale face recognition
Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao · 2016
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Women also snowboard: Overcoming bias in captioning models
L. Anne Hendricks, K. Burns, K. Saenko, T. Darrell, and A. Rohrbach · 2018
Later among the works it cites.
Gender shades: Intersectional accuracy disparities in commercial gender classification
J. Buolamwini and T. Gebru · 2018
Later among the works it cites.
Vggface2: A dataset for recognising faces across pose and age
Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman · 2018
Later among the works it cites.
Mitigating bias in gender, age and ethnicity classification: a multi-task convolution neural network approach
A. Das, A. Dantcheva, and F. Bremond · 2018
Later among the works it cites.
Squeeze-and-excitation networks
J. Hu, L. Shen, and G. Sun · 2018
Later among the works it cites.
Perception of an ambiguous figure is affected by own-age social biases
M. M. Nicholls, O. Churches, and T. Loetscher · 2018
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
The megaface benchmark: 1 million faces for recognition at scale
I. Kemelmacher-Shlizerman, S. M. Seitz, D. Miller, and E. Brossard · 2016
Cited alongside, same era.
Labeled faces in the wild: A survey
E. Learned-Miller, G. B. Huang, A. RoyChowdhury, H. Li, and G. Hua · 2016
Cited alongside, same era.
Learning deep features for discriminative localization
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba · 2016
Cited alongside, same era.
Finding tiny faces
P. Hu and D. Ramanan · 2017
Cited alongside, same era.
Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings
M. Alvi, A. Zisserman, and C. Nellåker · 2018
Cited alongside, same era.
https://tinyurl.com/y7rat8vb
Facial recognition, and bias
Cited in the paper.
Later among the works it cites.
Inclusivefacenet: Improving face attribute detection with race and gender diversity
H. J. Ryu, H. Adam, and M. Mitchell · 2018
Later among the works it cites.
Racial faces in-the-wild: Reducing racial bias by deep unsupervised domain adaptation
M. Wang, W. Deng, J. Hu, J. Peng, X. Tao, and Y. Huang · 2018
Later among the works it cites.
A light CNN for deep face representation with noisy labels
X. Wu, R. He, Z. Sun, and T. Tan · 2018
Later among the works it cites.
Actionable auditing: Investigating the impact of publicly naming biased performance results of commercial ai products
I. D. Raji and J. Buolamwini · 2019
Closest in time.
Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition
R. Ranjan, V. M. Patel, and R. Chellappa · 2019
Closest in time.