paper-with-me

홈 › Papers

Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition

2021-11-08 · Jiazhi Li, Wael Abd-Almageed

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor sufficient analysis for bias assessment metrics. We propose an information-theoretic, independent bias assessment metric to identify degree of bias against protected demographic attributes from learned representations of pretrained facial recognition systems. Our metric differs from other methods that rely on classification accuracy or examine the differences between ground truth and predicted labels of protected attributes predicted using a shallow network. Also, we argue, theoretically and experimentally, that logits-level loss is not adequate to explain bias since predictors based on neural networks will always find correlations. Further, we present a synthetic dataset that mitigates the issue of insufficient samples in certain cohorts. Lastly, we establish a benchmark metric by presenting advantages in clear discrimination and small variation comparing with other metrics, and evaluate the performance of different debiased models with the proposed metric.

📄 PDF Abstract BibTeX arXiv:2111.04673

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionFairness

Similar Papers 제목 키워드 기반

De-biased Representation Learning for Fairness with Unreliable Labels

2022-08-01 · Yixuan Zhang, Feng Zhou, Zhidong Li, Yang Wang 외

Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes co…

FairnessRepresentation Learning

Adversarial Scrubbing of Demographic Information for Text Classification

2021-09-17 · EMNLP 2021 11 · Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier B. Oliva 외

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirabl…

Classificationtext-classificationText Classification

Self-Supervised Representation Learning From Multi-Domain Data

2019-10-01 · ICCV 2019 10 · Zeyu Feng, Chang Xu, Dacheng Tao

We present an information-theoretically motivated constraint for self-supervised representation learning from multiple related domains. In contrast to previous self-supervised learning methods, our approach learns from m…

Representation LearningSelf-Supervised LearningTransfer Learning

Learning Fair Representations via Rate-Distortion Maximization

2022-01-31 · Somnath Basu Roy Chowdhury, Snigdha Chaturvedi

Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased dec…

AttributeFairness

Learning with Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration

2023-11-27 · Lei Wang, Qingbo Wu, Desen Yuan, King Ngi Ngan 외

Learning based image quality assessment (IQA) models have obtained impressive performance with the help of reliable subjective quality labels, where mean opinion score (MOS) is the most popular choice. However, in view o…

Image Quality Assessment