Related papers: Simple Calibration via Geodesic Kernels
Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, such as Stable Diffusion, we study the potential of generative…
Robust generalization under distribution shift remains difficult to monitor and optimize in the absence of target-domain labels, as models with similar in-distribution accuracy can exhibit markedly different out-of-distribution (OOD)…
Although Gaussian processes (GPs) with deep kernels have been successfully used for meta-learning in regression tasks, its uncertainty estimation performance can be poor. We propose a meta-learning method for calibrating deep kernel GPs for…
Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic…
We introduce a new deep generative model useful for uncertainty quantification: the Morse neural network, which generalizes the unnormalized Gaussian densities to have modes of high-dimensional submanifolds instead of just discrete points.…
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems. Despite the notable advancements in existing OOD detection methodologies, our study identifies a significant performance drop…
Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step…
Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…
In the recent literature on machine learning and decision making, calibration has emerged as a desirable and widely-studied statistical property of the outputs of binary prediction models. However, the algorithmic aspects of measuring model…
Comparing differently sized data sets is one main task in model assessment and calibration. This is due to field data being generally sparse compared to simulated model results. We tackled this task by the application of a new…
Pre-trained vision foundation models have transformed many computer vision tasks. Despite their strong ability to learn discriminative and generalizable features crucial for out-of-distribution (OOD) detection, their impact on this task…
Highly complex deep learning models are increasingly integrated into modern cyber-physical systems (CPS), many of which have strict safety requirements. One problem arising from this is that deep learning lacks interpretability, operating…
Image classification models deployed in the real world may receive inputs outside the intended data distribution. For critical applications such as clinical decision making, it is important that a model can detect such out-of-distribution…
While deep neural networks have made remarkable progress in various vision tasks, their performance typically deteriorates when tested in out-of-distribution (OOD) scenarios. Many OOD methods focus on extracting domain-invariant features…
Learning the embedding space, where semantically similar objects are located close together and dissimilar objects far apart, is a cornerstone of many computer vision applications. Existing approaches usually learn a single metric in the…
Many neural network-based out-of-distribution (OoD) detection methods have been proposed. However, they require many training data for each target task. We propose a simple yet effective meta-learning method to detect OoD with small…
The existing methods learn geographic network representations through deep graph neural networks (GNNs) based on the i.i.d. assumption. However, the spatial heterogeneity and temporal dynamics of geographic data make the out-of-distribution…
Deep neural networks (DNNs) have become a key part of many modern software applications. After training and validating, the DNN is deployed as an irrevocable component and applied in real-world scenarios. Although most DNNs are built…
Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model…
Detecting data points deviating from the training distribution is pivotal for ensuring reliable machine learning. Extensive research has been dedicated to the challenge, spanning classical anomaly detection techniques to contemporary…