Mitigating Bias in Gender, Age and Ethnicity Classification: A Multi-task Convolution Neural Network Approach

By Abhijit Das, Antitza Dantcheva, Francois Bremond. 2018

167 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, background): “Studies in algorithmic fairness have focused on either 1) discovering (auditing) existing bias in datasets or systems [50, 7, 30], 2) making a better dataset [39, 1], or 3) designing a better algorithm or model [12, 1, 47, 71, 70].”
Automatically Neutralizing Subjective Bias in Text (2019, background): “…prior research which has debiased representations of text by removing dimensions of prejudice from word embeddings (Bolukbasi et al. 2016; Gonen and Goldberg 2019; Ethayarajh, Duvenaud, and Hirst 2019) and the hidden states of predictive models (Zhao et al. 2018; Das, Dantcheva, and Bremond 2018).”
Taxonomizing and Measuring Representational Harms: A Look at Image Tagging (2023, background): “Some researchers have also taken an intersectional lens by focusing on different combinations of social groups (Buolamwini and Gebru 2018; Das, Dantcheva, and Bremond 2018).”
Towards causal benchmarking of bias in face analysis algorithms (2020, background): “The machine learning community is active in analyzing biases of learning models, and how one may train models where bias is mitigated [3, 14, 18, 31, 33, 41, 46, 51, 68], usually by ensuring that performance is equal across certain subgroups of a dataset.”
FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation (2021, background): “Studies in algorithmic fairness have focused on either 1) discovering (auditing) existing bias in datasets or systems [52, 7, 30, 39, 22], 2) making a better dataset [40, 1], or 3) designing a better algorithm or model [12, 1, 49, 72, 71, 62, 41, 27], typically by learning representations invariant ”
How We've Taught Algorithms to See Identity: Constructing Race and Gender in Image Databases for Facial Analysis (2020, background): “Machine learning researchers have proposed numerous statistical approaches (e.g., [35]) and toolkits (e.g., [17]) for mitigating bias.”