Related papers: Missingness Bias in Model Debugging

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

Identification of charged particles in a multilayer detector by the energy loss technique may also be achieved by the use of a neural network. The performance of the network becomes worse when a large fraction of information is missing, for…

The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time,…

We characterize the structure and origins of missingness for 159 cross-sectional return predictors and study missing value handling for portfolios constructed using machine learning. Simply imputing with cross-sectional means performs well…

Despite their successes in vision and language, foundation models have stumbled in pathology, revealing low accuracy, instability, and heavy computational demands. These shortcomings stem not from tuning problems but from deeper conceptual…

Although data may be abundant, complete data is less so, due to missing columns or rows. This missingness undermines the performance of downstream data products that either omit incomplete cases or create derived completed data for…

Blended light is an important source of degeneracy in the characterization of microlensing events, particularly in binary-lens and high magnification events. We show how the techniques of image subtraction can be applied to form an image of…

In this paper, we tackle interactive debugging of "gray-box" concept-based models (CBMs). These models learn task-relevant concepts appearing in the inputs and then compute a prediction by aggregating the concept activations. Our work stems…

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…

Over the past years, the crucial role of data has largely been shadowed by the field's focus on architectures and training procedures. We often cause changes to the data without being aware of their wider implications. In this paper we show…

This paper explores the null space properties of neural networks. We extend the null space definition from linear to nonlinear maps and discuss the presence of a null space in neural networks. The null space of a given neural network can…

With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified.…

The problem of algorithmic bias in machine learning has gained a lot of attention in recent years due to its concrete and potentially hazardous implications in society. In much the same manner, biases can also alter modern industrial and…

In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance. We describe why we consider reflection invariance to be an…

Image deblurring tries to eliminate degradation elements of an image causing blurriness and improve the quality of an image for better texture and object visualization. Traditionally, prior-based optimization approaches predominated in…

From face recognition in smartphones to automatic routing on self-driving cars, machine vision algorithms lie in the core of these features. These systems solve image based tasks by identifying and understanding objects, subsequently making…

Bias in image restoration algorithms can hamper further analysis, typically when the intensities have a physical meaning of interest, e.g., in medical imaging. We propose to suppress a part of the bias -- the method bias -- while leaving…

In the modern world, we are permanently using, leveraging, interacting with, and relying upon systems of ever higher sophistication, ranging from our cars, recommender systems in e-commerce, and networks when we go online, to integrated…

Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field. As these systems are increasingly being deployed in high-stakes real-world applications, there is a dire need to ensure…

Deep-learning models can extract a rich assortment of features from data. Which features a model uses depends not only on \emph{predictivity} -- how reliably a feature indicates training-set labels -- but also on \emph{availability} -- how…