相关论文: DASH: Visual Analytics for Debiasing Image Classif…

Data visualizations are powerful tools for communicating patterns in quantitative data. Yet understanding any data visualization is no small feat -- succeeding requires jointly making sense of visual, numerical, and linguistic inputs…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Machine learning models are known to perpetuate and even amplify the biases present in the data. However, these data biases frequently do not become apparent until after the models are deployed. Our work tackles this issue and enables the…

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…

Autonomous driving is a multi-task problem requiring a deep understanding of the visual environment. End-to-end autonomous systems have attracted increasing interest as a method of learning to drive without exhaustively programming…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities.…

The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…

A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical…

The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit…

There is a growing trend of applying machine learning methods to medical datasets in order to predict patients' future status. Although some of these methods achieve high performance, challenges still exist in comparing and evaluating…

The collection and visual analysis of large-scale data from complex systems, such as electronic health records or clickstream data, has become increasingly common across a wide range of industries. This type of retrospective visual…

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…

The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions of parameters, thus requiring extremely large datasets,…

Data-driven decision making has been a common task in today's big data era, from simple choices such as finding a fast way to drive home, to complex decisions on medical treatment. It is often supported by visual analytics. For various…

We propose a self-supervised training approach for learning view-invariant dense visual descriptors using image augmentations. Unlike existing works, which often require complex datasets, such as registered RGBD sequences, we train on an…

Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear…

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class…

The development of fair and ethical AI systems requires careful consideration of bias mitigation, an area often overlooked or ignored. In this study, we introduce a novel and efficient approach for addressing biases called Targeted Data…

One of the most useful techniques to help visual data analysis systems is interactive filtering (brushing). However, visualization techniques often suffer from overlap of graphical items and multiple attributes complexity, making visual…