no code implementations • 8 Mar 2023 • Bilal Porgali, Vítor Albiero, Jordan Ryda, Cristian Canton Ferrer, Caner Hazirbas
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annotators.
no code implementations • 12 Dec 2022 • Raghav Mehta, Vítor Albiero, Li Chen, Ivan Evtimov, Tamar Glaser, Zhiheng Li, Tal Hassner
With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.
no code implementations • 10 Nov 2022 • Caner Hazirbas, Yejin Bang, Tiezheng Yu, Parisa Assar, Bilal Porgali, Vítor Albiero, Stefan Hermanek, Jacqueline Pan, Emily McReynolds, Miranda Bogen, Pascale Fung, Cristian Canton Ferrer
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements.
no code implementations • 10 Jun 2022 • Aman Bhatta, Vítor Albiero, Kevin W. Bowyer, Michael C. King
We then demonstrate that when the data used to estimate recognition accuracy is balanced across gender for how hairstyles occlude the face, the initially observed gender gap in accuracy largely disappears.
3 code implementations • 4 Jun 2022 • Haiyu Wu, Vítor Albiero, K. S. Krishnapriya, Michael C. King, Kevin W. Bowyer
This is the first work that we are aware of to explore how the level of brightness of the skin region in a pair of face images (rather than a single image) impacts face recognition accuracy, and to evaluate this as a systematic factor causing unequal accuracy across demographics.
no code implementations • 29 Dec 2021 • Vítor Albiero, Kai Zhang, Michael C. King, Kevin W. Bowyer
There is consensus in the research literature that face recognition accuracy is lower for females, who often have both a higher false match rate and a higher false non-match rate.
no code implementations • 28 Apr 2021 • Ying Qiu, Vítor Albiero, Michael C. King, Kevin W. Bowyer
For impostor image pairs, our results show that pairs in which one image has a gender classification error have a better impostor distribution than pairs in which both images have correct gender classification, and so are less likely to generate a false match error.
2 code implementations • CVPR 2021 • Vítor Albiero, Xingyu Chen, Xi Yin, Guan Pang, Tal Hassner
Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators.
Ranked #6 on Head Pose Estimation on BIWI
no code implementations • 16 Aug 2020 • Vítor Albiero, Kevin W. Bowyer
There is consensus in the research literature that face recognition accuracy is lower for females, who often have both a higher false match rate and a higher false non-match rate.
2 code implementations • 7 Apr 2020 • Kai Zhang, Vítor Albiero, Kevin W. Bowyer
The numbers of subjects and images acquired in web-scraped datasets are usually very large, with number of images on the millions scale.
1 code implementation • 7 Feb 2020 • Vítor Albiero, Kai Zhang, Kevin W. Bowyer
Deep learning methods have greatly increased the accuracy of face recognition, but an old problem still persists: accuracy is usually higher for men than women.
no code implementations • 31 Jan 2020 • Vítor Albiero, Krishnapriya K. S., Kushal Vangara, Kai Zhang, Michael C. King, Kevin W. Bowyer
We show that the female genuine distribution improves when only female images without facial cosmetics are used, but that the female impostor distribution also degrades at the same time.
no code implementations • 20 Dec 2019 • Vítor Albiero, Nisha Srinivas, Esteban Villalobos, Jorge Perez-Facuse, Roberto Rosenthal, Domingo Mery, Karl Ricanek, Kevin W. Bowyer
Matching live images (``selfies'') to images from ID documents is a problem that can arise in various applications.
no code implementations • 14 Nov 2019 • Vítor Albiero, Kevin W. Bowyer, Kushal Vangara, Michael C. King
In contrast, a pre deep learning matcher on the same dataset shows the traditional result of higher accuracy for older persons, although its overall accuracy is much lower than that of the deep learning matchers.