Related papers: Data Coverage for Detecting Representation Bias in…

In machine learning and computer vision, input images are often filtered to increase data discriminability. In some situations, however, one may wish to purposely decrease discriminability of one classification task (a "distractor" task),…

Over the last decades, hand-crafted feature extractors have been used to encode image visual properties into feature vectors. Recently, data-driven feature learning approaches have been successfully explored as alternatives for producing…

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd…

In real world datasets, particular groups are under-represented, much rarer than others, and machine learning classifiers will often preform worse on under-represented populations. This problem is aggravated across many domains where…

Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…

Imbalanced data classification problem has always been a popular topic in the field of machine learning research. In order to balance the samples between majority and minority class. Oversampling algorithm is used to synthesize new minority…

Image segmentation is an important component of many image understanding systems. It aims to group pixels in a spatially and perceptually coherent manner. Typically, these algorithms have a collection of parameters that control the degree…

The ProbCover method of Yehuda et al. is a well-motivated algorithm for active learning in low-budget regimes, which attempts to "cover" the data distribution with balls of a given radius at selected data points. We demonstrate, however,…

Clustering is an unsupervised learning task that aims to partition data into a set of clusters. In many applications, these clusters correspond to real-world constructs (e.g. electoral districts) whose benefit can only be attained by groups…

Bias discovery is critical for black-box generative models, especiall text-to-image (TTI) models. Existing works predominantly focus on output-level demographic distributions, which do not necessarily guarantee concept representations to be…

JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to significant accuracy…

Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections. The number of available datasets is still progressively growing together with the amount of samples…

Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets…

Considerations of bias, fairness and representation are a prerequisite of responsible modern statistics. In statistical network analysis, observed networks are often incomplete or systematically biased, which can lead to systematic…

Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthiness of FRS, more recent efforts have tried to find the causes. However, these studies make…

In this paper, we propose a novel explanatory framework aimed to provide a better understanding of how face recognition models perform as the underlying data characteristics (protected attributes: gender, ethnicity, age; non-protected…

We explore varying face recognition accuracy across demographic groups as a phenomenon partly caused by differences in face illumination. We observe that for a common operational scenario with controlled image acquisition, there is a large…

Image classification is a challenging problem for computer in reality. Large numbers of methods can achieve satisfying performances with sufficient labeled images. However, labeled images are still highly limited for certain image…

This paper considers the problem of representative selection: choosing a subset of data points from a dataset that best represents its overall set of elements. This subset needs to inherently reflect the type of information contained in the…

The size of large, geo-located datasets has reached scales where visualization of all data points is inefficient. Random sampling is a method to reduce the size of a dataset, yet it can introduce unwanted errors. We describe a method for…