Related papers: Discover the Unknown Biased Attribute of an Image …

Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of…

Ensuring trust and accountability in Artificial Intelligence systems demands explainability of its outcomes. Despite significant progress in Explainable AI, human biases still taint a substantial portion of its training data, raising…

Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark datasets make it…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it…

Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

A person downloading a pre-trained model from the web should be aware of its biases. Existing approaches for bias identification rely on datasets containing labels for the task of interest, something that a non-expert may not have access…

The detection of AI-generated faces is commonly approached as a binary classification task. Nevertheless, the resulting detectors frequently struggle to adapt to novel AI face generators, which evolve rapidly. In this paper, we describe an…

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…

We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the training set, we aim to unlearn a specific feature, such as…

Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…

We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an…

As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Reliably detecting diseases using relevant biological information is crucial for real-world applicability of deep learning techniques in medical imaging. We debias deep learning models during training against unknown bias - without…

In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent…

Image classifiers often rely overly on peripheral attributes that have a strong correlation with the target class (i.e., dataset bias) when making predictions. Due to the dataset bias, the model correctly classifies data samples including…

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…