Fair Attribute Classification through Latent Space De-biasing

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes (e.g., gender, race) are known to learn and exploit those correlations. In this work, we introduce a method for training accurate target classifiers while mitigating biases that stem from these correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We augment the original dataset with this perturbed generated data, and empirically demonstrate that target classifiers trained on the augmented dataset exhibit a number of both quantitative and qualitative benefits. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space.

[1]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[2]  Jinwoo Shin,et al.  Learning from Failure: Training Debiased Classifier from Biased Classifier , 2020, ArXiv.

[3]  Charles Elkan,et al.  The Foundations of Cost-Sensitive Learning , 2001, IJCAI.

[4]  Steffen Bickel,et al.  Discriminative Learning Under Covariate Shift , 2009, J. Mach. Learn. Res..

[5]  Olga Russakovsky,et al.  REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets , 2020, International Journal of Computer Vision.

[6]  Andrew Zisserman,et al.  Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings , 2018, ECCV Workshops.

[7]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[8]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[9]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  Jieyu Zhao,et al.  Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints , 2017, EMNLP.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

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

[13]  Bolei Zhou,et al.  Seeing What a GAN Cannot Generate , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  Hee Jung Ryu,et al.  InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity , 2017 .

[15]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[16]  Kush R. Varshney,et al.  Fairness GAN , 2018, IBM Journal of Research and Development.

[17]  Lu Zhang,et al.  FairGAN: Fairness-aware Generative Adversarial Networks , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[18]  Emily Denton,et al.  Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias , 2019 .

[19]  Olga Russakovsky,et al.  Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Olga Russakovsky,et al.  Directional Bias Amplification , 2021, ICML.

[21]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Peter Wonka,et al.  Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space? , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[23]  David Bau,et al.  Diverse Image Generation via Self-Conditioned GANs , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[26]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Bolei Zhou,et al.  Interpreting the Latent Space of GANs for Semantic Face Editing , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Vishnu Suresh Lokhande,et al.  FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret , 2020, ECCV.

[29]  Stefano Ermon,et al.  Fair Generative Modeling via Weak Supervision , 2020, ICML.

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

[31]  Mingliang Chen,et al.  Towards Threshold Invariant Fair Classification , 2020, UAI.

[32]  Zengchang Qin,et al.  Emotion Classification with Data Augmentation Using Generative Adversarial Networks , 2018, PAKDD.

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

[34]  Meisam Razaviyayn,et al.  Rényi Fair Inference , 2019, ICLR.

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

[36]  Bharath Hariharan,et al.  Low-Shot Visual Recognition by Shrinking and Hallucinating Features , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Trevor Darrell,et al.  Contrastive Examples for Addressing the Tyranny of the Majority , 2020, ArXiv.

[38]  Jieyu Zhao,et al.  Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[40]  Fei-Fei Li,et al.  Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy , 2019, FAT*.

[41]  Trevor Darrell,et al.  Women also Snowboard: Overcoming Bias in Captioning Models , 2018, ECCV.

[42]  Pietro Perona,et al.  Towards causal benchmarking of bias in face analysis algorithms , 2020, ECCV.

[43]  Rachel K. E. Bellamy,et al.  AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias , 2018, ArXiv.

[44]  Deli Zhao,et al.  In-Domain GAN Inversion for Real Image Editing , 2020, ECCV.

[45]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[46]  Blake Lemoine,et al.  Mitigating Unwanted Biases with Adversarial Learning , 2018, AIES.