Gender Classification and Bias Mitigation in Facial Images

Wang, Wenying; Protopapas, Pavlos; Yang, Zheng; Michalatos, Panagiotis

doi:10.1145/3394231.3397900

Cited by 27 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [85] collected two benchmark datasets: the Inclusive Benchmark Database (IBD), and Non-binary Gender Benchmark Database (NGBD) 24 . IBD contains 12,000 images of 168 different subjects, 21 of which identify as LGBTQ.…”

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

“…Thus, the database contains multiple gender identities (namely: non-binary, genderfluid, genderqueer, gender non-conforming, agender, gender neutral, gender-less, third gender, and queer ). The authors themselves identify two major risks of label bias: first, "Gender identity has its multifaceted aspects that a simple label could not categorize" [85] (the authors identify the problem of modelling gender as a continuum as a direction for future work); and, second, "Gender is a complex socio-cultural construct and an internal identity that is not necessarily tied to physical appearances." [85].…”

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

“…The authors themselves identify two major risks of label bias: first, "Gender identity has its multifaceted aspects that a simple label could not categorize" [85] (the authors identify the problem of modelling gender as a continuum as a direction for future work); and, second, "Gender is a complex socio-cultural construct and an internal identity that is not necessarily tied to physical appearances." [85]. Hazirbas et al [33] proposed the Casual Conversations Dataset for evaluating the performance of CV models across different demographic categories.…”

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Bias in Visual Datasets

Fabbrizzi¹,

Papadopoulos²,

Ntoutsi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in major discrimination if not dealt with proper care. CV systems highly depend on the data they are fed with and can learn and amplify biases within such data. Thus, both the problems of understanding and discovering biases are of utmost importance. Yet, to date there is no comprehensive survey on bias in visual datasets. To this end, this work aims to: i) describe the biases that can affect visual datasets; ii) review the literature on methods for bias discovery and quantification in visual datasets; iii) discuss existing attempts to collect bias-aware visual datasets. A key conclusion of our study is that the problem of bias discovery and quantification in visual datasets is still open and there is room for improvement in terms of both methods and the range of biases that can be addressed; moreover, there is no such thing as a bias-free dataset, so scientists and practitioners must become aware of the biases in their datasets and make them explicit. To this end, we propose a checklist that can be used to spot different types of bias during visual dataset collection.

show abstract

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

Section: Datasets Buolamwini and Gebrumentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Bias in Visual Datasets

Fabbrizzi¹,

Papadopoulos²,

Ntoutsi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There has been an increased desire for privacy regarding facial analysis, and demographic data is usually considered a sensitive attribute. Facial analysis, such as gender classification, has also been seen to have high error rates in LGBTQ+, and non-binary individuals [16]. Moreover, in [1], Qiu et al, found that false classifications of gender correlate with a false rejection of a true matching.…”

Section: Introductionmentioning

confidence: 99%

Fair Face Verification by Using Non-Sensitive Soft-Biometric Attributes

2022

View full text Add to dashboard Cite

Facial recognition has been shown to have different accuracy for different demographic groups. When setting a threshold to achieve a specific False Match Rate (FMR) on a mixed demographic impostor distribution, some demographic groups can experience a significantly worse FMR. To mitigate this, some authors have proposed to use demographic-specific thresholds. However, this can be impractical in an operational scenario, as it would either require users to report their demographic group or the system to predict the demographic group of each user. Both of these options can be deemed controversial since the demographic group is a sensitive attribute. Further, this approach requires listing the possible demographic groups, which can become controversial in itself. We show that a similar mitigation effect can be achieved using non-sensitive predicted soft-biometric attributes. These attributes are based on the appearance of the users (such as hairstyle, accessories, and facial geometry) rather than how the users self-identify. Our experiments use a set of 38 binary non-sensitive attributes from the MAAD-Face dataset. We report results on the Balanced Faces in the Wild dataset, which has a balanced number of identities by race and gender. We compare clustering-based and decision-tree-based strategies for selecting thresholds. We show that the proposed strategies can reduce differential outcomes in intersectional groups twice as effectively as using gender-specific thresholds and, in some cases, are also better than using race-specific thresholds.

show abstract

“…Bias and mitigation strategies in facial analysis have attracted increasing attention both from the general public and the research communities. For example, many studies have investigated bias and mitigation strategies for face recognition [5,12,13,14,35,38,41], gender recognition [8,12,43,50], age estimation [6,8,12,16,43], kinship verification [12] and face image quality estimation [44]. However, bias in facial expression recognition has not been investigated, except for [9,49], that only focussed on the task of smiling/non-smiling using the CelebA dataset.…”

Section: Introductionmentioning

confidence: 99%

Investigating Bias and Fairness in Facial Expression Recognition

White

Kalkan

et al. 2020

Preprint

View full text Add to dashboard Cite

Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and corresponding expression labels. However, virtually none of these datasets have been acquired with consideration of fair distribution across the human population. Therefore, in this work, we undertake a systematic investigation of bias and fairness in facial expression recognition by comparing three different approaches, namely a baseline, an attribute-aware and a disentangled approach, on two wellknown datasets, RAF-DB and CelebA. Our results indicate that: (i) data augmentation improves the accuracy of the baseline model, but this alone is unable to mitigate the bias effect; (ii) both the attribute-aware and the disentangled approaches equipped with data augmentation perform better than the baseline approach in terms of accuracy and fairness; (iii) the disentangled approach is the best for mitigating demographic bias; and (iv) the bias mitigation strategies are more suitable in the existence of uneven attribute distribution or imbalanced number of subgroup data.

show abstract

Gender Classification and Bias Mitigation in Facial Images

Cited by 27 publications

References 18 publications

A Survey on Bias in Visual Datasets

A Survey on Bias in Visual Datasets

Fair Face Verification by Using Non-Sensitive Soft-Biometric Attributes

Investigating Bias and Fairness in Facial Expression Recognition

Contact Info

Product

Resources

About