Enhancing Facial Data Diversity with Style-based Face Aging
- URL: http://arxiv.org/abs/2006.03985v1
- Date: Sat, 6 Jun 2020 21:53:44 GMT
- Title: Enhancing Facial Data Diversity with Style-based Face Aging
- Authors: Markos Georgopoulos, James Oldfield, Mihalis A. Nicolaou, Yannis
Panagakis, Maja Pantic
- Abstract summary: In particular, face datasets are typically biased in terms of attributes such as gender, age, and race.
We propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns.
We show that the proposed method outperforms state-of-the-art algorithms for age transfer.
- Score: 59.984134070735934
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A significant limiting factor in training fair classifiers relates to the
presence of dataset bias. In particular, face datasets are typically biased in
terms of attributes such as gender, age, and race. If not mitigated, bias leads
to algorithms that exhibit unfair behaviour towards such groups. In this work,
we address the problem of increasing the diversity of face datasets with
respect to age. Concretely, we propose a novel, generative style-based
architecture for data augmentation that captures fine-grained aging patterns by
conditioning on multi-resolution age-discriminative representations. By
evaluating on several age-annotated datasets in both single- and cross-database
experiments, we show that the proposed method outperforms state-of-the-art
algorithms for age transfer, especially in the case of age groups that lie in
the tails of the label distribution. We further show significantly increased
diversity in the augmented datasets, outperforming all compared methods
according to established metrics.
Related papers
- Toward responsible face datasets: modeling the distribution of a
disentangled latent space for sampling face images from demographic groups [0.0]
Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups.
We propose to use a simple method for modeling and sampling a disentangled projection of a StyleGAN latent space to generate any combination of demographic groups.
Our experiments show that we can synthesis any combination of demographic groups effectively and the identities are different from the original training dataset.
arXiv Detail & Related papers (2023-09-15T14:42:04Z) - Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.
We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes.
We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
arXiv Detail & Related papers (2023-08-28T18:48:34Z) - Deep Learning on a Healthy Data Diet: Finding Important Examples for
Fairness [15.210232622716129]
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes.
Data augmentation reduces gender bias by adding counterfactual examples to the training dataset.
We show that some of the examples in the augmented dataset can be not important or even harmful for fairness.
arXiv Detail & Related papers (2022-11-20T22:42:30Z) - Addressing Bias in Face Detectors using Decentralised Data collection
with incentives [0.0]
We show how this data-centric approach can be facilitated in a decentralized manner to enable efficient data collection for algorithms.
We propose a face detection and anonymization approach using a hybrid MultiTask Cascaded CNN with FaceNet Embeddings.
arXiv Detail & Related papers (2022-10-28T09:54:40Z) - Rethinking Data Heterogeneity in Federated Learning: Introducing a New
Notion and Standard Benchmarks [65.34113135080105]
We show that not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants.
Our observations are intuitive.
Our code is available at https://github.com/MMorafah/FL-SC-NIID.
arXiv Detail & Related papers (2022-09-30T17:15:19Z) - Assessing Demographic Bias Transfer from Dataset to Model: A Case Study
in Facial Expression Recognition [1.5340540198612824]
Two metrics focus on the representational and stereotypical bias of the dataset, and the third one on the residual bias of the trained model.
We demonstrate the usefulness of the metrics by applying them to a FER problem based on the popular Affectnet dataset.
arXiv Detail & Related papers (2022-05-20T09:40:42Z) - Reducing Racial Bias in Facial Age Prediction using Unsupervised Domain
Adaptation in Regression [0.0]
We propose an approach for unsupervised domain adaptation for the task of estimating someone's age from a given face image.
In order to avoid the propagation of racial bias in most publicly available face image datasets, we perform domain adaptation to motivate the predictor to learn features that are invariant to ethnicity.
arXiv Detail & Related papers (2021-04-05T05:31:12Z) - Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
There are demographic biases present in current facial recognition (FR) models.
We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups.
We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results.
We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
arXiv Detail & Related papers (2021-03-16T15:05:49Z) - Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
This work aims to learn a fair face representation, where faces of every group could be more equally represented.
Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
arXiv Detail & Related papers (2020-06-13T06:43:37Z) - Contrastive Examples for Addressing the Tyranny of the Majority [83.93825214500131]
We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened.
We show that current generative adversarial networks are a powerful tool for learning these data points, called contrastive examples.
arXiv Detail & Related papers (2020-04-14T14:06:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.