Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

The paper “Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification” by Joy Buolamwini and Timnit Gebru, that will be presented at the Conference on Fairness, Accountability, and Transparency (FAT*) in February 2018, evaluates three commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition. The study finds these services to have recognition capabilities that are not balanced over genders and skin tones [1]. In particular, the authors show that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men.

[1]  T. Fitzpatrick.  The validity and practicality of sun-reactive skin types I through VI. , 1988, Archives of dermatology.

[2]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[3]  L. Roth.  Looking at Shirley, the Ultimate Norm: Colour Balance, Image Technologies, and Cognitive Equity , 2009 .

[4]  Alice J. O'Toole,et al.  An other-race effect for face recognition algorithms , 2011, TAP.

[5]  Anil K. Jain,et al.  Face Recognition Performance: Role of Demographic Information , 2012, IEEE Transactions on Information Forensics and Security.

[6]  J. Dugelay,et al.  Demographic classification: Do gender and ethnicity affect each other? , 2012, 2012 International Conference on Informatics, Electronics & Vision (ICIEV).

[7]  Arun Ross,et al.  Soft biometrics for surveillance: an overview , 2013 .

[8]  Luc Van Gool,et al.  Face Detection without Bells and Whistles , 2014, ECCV.

[9]  Anil K. Jain,et al.  Age , Gender and Race Estimation from Unconstrained Face Images , 2014 .

[10]  Shan Sung Liew,et al.  Convolutional Neural Network for Face Recognition with Pose and Illumination Variation , 2014 .

[11]  Frank A. Pasquale,et al.  [89WashLRev0001] The Scored Society: Due Process for Automated Predictions , 2014 .

[12]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[13]  Pierluigi Carcagnì,et al.  Automatic Emotion Recognition in Robot-Children Interaction for ASD Treatment , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[14]  Patrick J. Grother,et al.  Face Recognition Vendor Test (FRVT) - Performance of Automated Gender Classification Algorithms , 2015 .

[15]  David A. Shamma,et al.  The New Data and New Challenges in Multimedia Research , 2015, ArXiv.

[16]  Anil K. Jain,et al.  Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[18]  Mita Nasipuri,et al.  Illumination, Pose and Occlusion Invariant Face Recognition from Range Images Using ERFI Model , 2015, Int. J. Syst. Dyn. Appl..

[19]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2016, International Journal of Computer Vision.

[20]  Xi Zhang,et al.  Automated Inference on Criminality using Face Images , 2016, ArXiv.

[21]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[22]  Ira Kemelmacher-Shlizerman,et al.  The MegaFace Benchmark: 1 Million Faces for Recognition at Scale , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Mohamed Chetouani,et al.  A multimodal and multilevel system for robotics treatment of autism in children , 2016, DAA '16.

[24]  Julie D. Golomb,et al.  A Neural Basis of Facial Action Recognition in Humans , 2016, The Journal of Neuroscience.

[25]  Aleix M. Martínez,et al.  EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of a Million Facial Expressions in the Wild , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[27]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[28]  Kush R. Varshney,et al.  Optimized Pre-Processing for Discrimination Prevention , 2017, NIPS.

[29]  Tony Doyle,et al.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2017, Inf. Soc..

[30]  Ioannis A. Kakadiaris,et al.  3D-2D face recognition with pose and illumination normalization , 2017, Comput. Vis. Image Underst..

[31]  Kush R. Varshney,et al.  An End-To-End Machine Learning Pipeline That Ensures Fairness Policies , 2017, ArXiv.

[32]  Carlos D. Castillo,et al.  An All-In-One Convolutional Neural Network for Face Analysis , 2016, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[33]  Bernard Ghanem,et al.  Multi-scale Fully Convolutional Network for Face Detection in the Wild , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[34]  Afshin Dehghan,et al.  DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network , 2017, ArXiv.

[35]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[36]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[37]  Bernhard Schölkopf,et al.  Avoiding Discrimination through Causal Reasoning , 2017, NIPS.

[38]  Francesca Rossi,et al.  Towards Composable Bias Rating of AI Services , 2018, AIES.

[39]  Sameep Mehta,et al.  Analyze, Detect and Remove Gender Stereotyping from Bollywood Movies , 2018, FAT.