相关论文: Balanced Datasets Are Not Enough: Estimating and M…

We investigate the impact of deep generative models on potential social biases in upcoming computer vision models. As the internet witnesses an increasing influx of AI-generated images, concerns arise regarding inherent biases that may…

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…

Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the reported dataset than can be replicated on other datasets. Even…

Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as full-supervision, which has two limitations: 1) it is…

Dataset biases are notoriously detrimental to model robustness and generalization. The identify-emphasize paradigm appears to be effective in dealing with unknown biases. However, we discover that it is still plagued by two challenges: A,…

Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. We introduce a new…

Recent developments in machine learning have shown that successful models do not rely only on huge amounts of data but the right kind of data. We show in this paper how this data-centric approach can be facilitated in a decentralized manner…

Gender classification aims at recognizing a person's gender. Despite the high accuracy achieved by state-of-the-art methods for this task, there is still room for improvement in generalized and unrestricted datasets. In this paper, we…

Interpreting the inference-time behavior of deep neural networks remains a challenging problem. Existing approaches to counterfactual explanation typically ask: What is the closest alternative input that would alter the model's prediction…

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…

Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the…

Dataset bias remains a significant barrier towards solving real world computer vision tasks. Though deep convolutional networks have proven to be a competitive approach for image classification, a question remains: have these models have…

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…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias amplification metrics (e.g., BA (MALS), DPA) measure bias…

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

Imperfect labels limit the quality of predictions learned by deep neural networks. This is particularly relevant in medical image segmentation, where reference annotations are difficult to collect and vary significantly even across expert…

Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using…