Related papers: Meta Balanced Network for Fair Face Recognition
Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation…
Modern approaches for semantic segmention usually pay too much attention to the accuracy of the model, and therefore it is strongly recommended to introduce cumbersome backbones, which brings heavy computation burden and memory footprint.…
Robust face detection is one of the most important pre-processing steps to support facial expression analysis, facial landmarking, face recognition, pose estimation, building of 3D facial models, etc. Although this topic has been intensely…
We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and…
Attribute recognition, particularly facial, extracts many labels for each image. While some multi-task vision problems can be decomposed into separate tasks and stages, e.g., training independent models for each task, for a growing set of…
Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to…
Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial learning. A discriminator is used to identify the bias…
With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…
Person re-identification aims to match images of the same person across disjoint camera views, which is a challenging problem in video surveillance. The major challenge of this task lies in how to preserve the similarity of the same person…
Bias can be introduced to AI systems even from seemingly balanced sources, and AI facial beauty prediction is subject to ethnicity-based bias. This work sounds warnings about AI's role in shaping aesthetic norms while providing potential…
We reveal critical insights into problems of bias in state-of-the-art facial recognition (FR) systems using a novel Balanced Faces In the Wild (BFW) dataset: data balanced for gender and ethnic groups. We show variations in the optimal…
Artificial intelligence (AI) has shown remarkable promise in dermatology, offering accurate and non-invasive diagnosis of skin cancer. While extensive research has addressed skin tone-related bias, gender bias in dermatologic AI remains…
Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and…
This project explores adversarial training techniques to develop fairer Deep Neural Networks (DNNs) to mitigate the inherent bias they are known to exhibit. DNNs are susceptible to inheriting bias with respect to sensitive attributes such…
Skin recognition is used in many applications ranging from algorithms for face detection, hand gesture analysis, and to objectionable image filtering. In this work a skin recognition system was developed and tested. While many skin…
All datasets contain some biases, often unintentional, due to how they were acquired and annotated. These biases distort machine-learning models' performance, creating spurious correlations that the models can unfairly exploit, or,…
Published research highlights the presence of demographic bias in automated facial attribute classification algorithms, particularly impacting women and individuals with darker skin tones. Existing bias mitigation techniques typically…
Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not…
This paper addresses the problem of automatically detecting human skin in images without reliance on color information. A primary motivation of the work has been to achieve results that are consistent across the full range of skin tones,…
When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known…