相关论文: InsideBias: Measuring Bias in Deep Networks and Ap…

This paper is the first to explore an automatic way to detect bias in deep convolutional neural networks by simply looking at their weights. Furthermore, it is also a step towards understanding neural networks and how they work. We show…

Deep learning-based methods have pushed the limits of the state-of-the-art in face analysis. However, despite their success, these models have raised concerns regarding their bias towards certain demographics. This bias is inflicted both by…

Do very high accuracies of deep networks suggest pride of effective AI or are deep networks prejudiced? Do they suffer from in-group biases (own-race-bias and own-age-bias), and mimic the human behavior? Is in-group specific information…

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework…

A critical problem in deep learning is that systems learn inappropriate biases, resulting in their inability to perform well on minority groups. This has led to the creation of multiple algorithms that endeavor to mitigate bias. However, it…

Common studies of gender bias in NLP focus either on extrinsic bias measured by model performance on a downstream task or on intrinsic bias found in models' internal representations. However, the relationship between extrinsic and intrinsic…

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…

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

Recent studies have demonstrated that deep learning models can discriminate based on protected classes like race and gender. In this work, we evaluate bias present in deepfake datasets and detection models across protected subgroups. Using…

Deep learning (DL) models are widely used to provide a more convenient and smarter life. However, biased algorithms will negatively influence us. For instance, groups targeted by biased algorithms will feel unfairly treated and even fearful…

Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of…

Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on…

As deep learning models become tasked with more and more decisions that impact human lives, such as criminal recidivism, loan repayment, and face recognition for law enforcement, bias is becoming a growing concern. Debiasing algorithms are…

In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that trained models significantly amplify the association of target…

Over the past decades the machine and deep learning community has celebrated great achievements in challenging tasks such as image classification. The deep architecture of artificial neural networks together with the plenitude of available…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases.…

Rapid development of artificial intelligence (AI) systems amplify many concerns in society. These AI algorithms inherit different biases from humans due to mysterious operational flow and because of that it is becoming adverse in usage. As…

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…

Neural compression methods are gaining popularity due to their superior rate-distortion performance over traditional methods, even at extremely low bitrates below 0.1 bpp. As deep learning architectures, these models are prone to bias…