Does Object Recognition Work for Everyone?

The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset. This dataset contains household items and was designed to have a more representative geographical coverage than commonly used image datasets in object recognition. We find that the systems perform relatively poorly on household items that commonly occur in countries with a low household income. Qualitative analyses suggest the drop in performance is primarily due to appearance differences within an object class (e.g., dish soap) and due to items appearing in a different context (e.g., toothbrushes appearing outside of bathrooms). The results of our study suggest that further work is needed to make object-recognition systems work equally well for people across different countries and income levels.

[1]  Kristian Lum,et al.  An algorithm for removing sensitive information: Application to race-independent recidivism prediction , 2017, The Annals of Applied Statistics.

[2]  D. Sculley,et al.  No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World , 2017, 1711.08536.

[3]  Jiebo Luo,et al.  VizWiz Grand Challenge: Answering Visual Questions from Blind People , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[5]  Max Welling,et al.  The Variational Fair Autoencoder , 2015, ICLR.

[6]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[7]  Ofir Nachum,et al.  Identifying and Correcting Label Bias in Machine Learning , 2019, AISTATS.

[8]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[9]  Avi Feller,et al.  Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[10]  Jordi Pont-Tuset,et al.  The Open Images Dataset V4 , 2018, International Journal of Computer Vision.

[11]  Moustapha Cissé,et al.  ConvNets and ImageNet Beyond Accuracy: Explanations, Bias Detection, Adversarial Examples and Model Criticism , 2017, ArXiv.

[12]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[13]  Sean A. Munson,et al.  Unequal Representation and Gender Stereotypes in Image Search Results for Occupations , 2015, CHI.

[14]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[15]  Barbara Caputo,et al.  A Deeper Look at Dataset Bias , 2015, Domain Adaptation in Computer Vision Applications.

[16]  R. Zemel,et al.  THE VARIATIONAL FAIR AUTO ENCODER , 2015 .

[17]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[18]  Toon Calders,et al.  Classifying without discriminating , 2009, 2009 2nd International Conference on Computer, Control and Communication.

[19]  Suresh Venkatasubramanian,et al.  Auditing black-box models for indirect influence , 2016, Knowledge and Information Systems.

[20]  Jon M. Kleinberg,et al.  Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.

[21]  Alexandra Chouldechova,et al.  Fair prediction with disparate impact: A study of bias in recidivism prediction instruments , 2016, Big Data.

[22]  Suresh Venkatasubramanian,et al.  Auditing Black-Box Models for Indirect Influence , 2016, ICDM.

[23]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[24]  Jun Sakuma,et al.  Fairness-aware Learning through Regularization Approach , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[25]  Krishna P. Gummadi,et al.  Learning Fair Classifiers , 2015, 1507.05259.

[26]  Jon M. Kleinberg,et al.  On Fairness and Calibration , 2017, NIPS.

[27]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[29]  Toon Calders,et al.  Building Classifiers with Independency Constraints , 2009, 2009 IEEE International Conference on Data Mining Workshops.

[30]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[31]  Baoyuan Wu,et al.  Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning , 2019, IEEE Access.

[32]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[33]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[34]  Laura Martin.  “Eskimo Words for Snow”: A Case Study in the Genesis and Decay of an Anthropological Example , 1986 .

[35]  Guillaume Lample,et al.  Word Translation Without Parallel Data , 2017, ICLR.

[36]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[37]  Toon Calders,et al.  Three naive Bayes approaches for discrimination-free classification , 2010, Data Mining and Knowledge Discovery.

[38]  Inioluwa Deborah Raji,et al.  Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products , 2019, AIES.

[39]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Radomír Mech,et al.  Recognizing and Curating Photo Albums via Event-Specific Image Importance , 2017, BMVC.

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

[42]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.