Related papers: Multiple Distribution Shift -- Aerial (MDS-A): A D…

For autonomous vehicles to viably replace human drivers they must contend with inclement weather. Falling rain and snow introduce noise in LiDAR returns resulting in both false positive and false negative object detections. In this article…

Generalizing the application of machine learning models to situations where the statistical distribution of training and test data are different has been a complex problem. Our contributions in this paper are threefold: (1) we introduce an…

Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomaly detection methods for categorical, mixed-type, and…

The boom of DL technology leads to massive DL models built and shared, which facilitates the acquisition and reuse of DL models. For a given task, we encounter multiple DL models available with the same functionality, which are considered…

Decisions made by machine learning systems have increasing influence on the world, yet it is common for machine learning algorithms to assume that no such influence exists. An example is the use of the i.i.d. assumption in content…

Cyber-physical systems (CPS) greatly benefit by using machine learning components that can handle the uncertainty and variability of the real-world. Typical components such as deep neural networks, however, introduce new types of hazards…

We categorize meta-learning evaluation into two settings: $\textit{in-distribution}$ [ID], in which the train and test tasks are sampled $\textit{iid}$ from the same underlying task distribution, and $\textit{out-of-distribution}$ [OOD], in…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Clouds play a key role in regulating climate change but are difficult to simulate within Earth system models (ESMs). Improving the representation of clouds is one of the key tasks towards more robust climate change projections. This study…

Laboratory experiments and theoretical modelling are conducted to determine the raindrop size distribution (DSD) resulting from distinct fragmentation processes under various upward airstreams. Since weather radar echoes are proportional to…

Materials property prediction models are usually evaluated using random splitting of datasets into training and test datasets, which not only leads to over-estimated performance due to inherent redundancy, typically existent in material…

Domain adaptation algorithms are useful when the distributions of the training and the test data are different. In this paper, we focus on the problem of instrumental variation and time-varying drift in the field of sensors and measurement,…

Background: Machine learning (ML) methods often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices in clinical settings, where data drift may cause unexpected performance that…

Online updating of time series forecasting models aims to tackle the challenge of concept drifting by adjusting forecasting models based on streaming data. While numerous algorithms have been developed, most of them focus on model design…

The generation of initial conditions via accurate data assimilation is crucial for weather forecasting and climate modeling. We propose DiffDA as a denoising diffusion model capable of assimilating atmospheric variables using predicted…

The utility of aerial imagery (Satellite, Drones) has become an invaluable information source for cross-disciplinary applications, especially for crisis management. Most of the mapping and tracking efforts are manual which is…

We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution dynamics. This is relevant to applications in control,…

Recent remarkable success in the deep-learning industries has unprecedentedly increased the need for reliable model deployment. For example, the model should alert the user if the produced model outputs might not be reliable. Previous…

Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces a geometric failure mode, Domain-Sensitivity Collapse (DSC):…

Predictive uncertainty estimation is essential for safe deployment of Deep Neural Networks in real-world autonomous systems. However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially…