Related papers: Out-of-Distribution Robustness with Deep Recursive…

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how…

Stochastic programs where the uncertainty distribution must be inferred from noisy data samples are considered. The stochastic programs are approximated with distributionally-robust optimizations that minimize the worst-case expected cost…

As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for…

Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques…

Recent advances in neural information retrieval (IR) models have significantly enhanced their effectiveness over various IR tasks. The robustness of these models, essential for ensuring their reliability in practice, has also garnered…

Traversing terrain with good traction is crucial for achieving fast off-road navigation. Instead of manually designing costs based on terrain features, existing methods learn terrain properties directly from data via self-supervision to…

Real-world network applications must cope with failing nodes, malicious attacks, or nodes facing corrupted data - data classified as outliers. Our work addresses these concerns in the scope of the sensor network localization problem where,…

Out-of-distribution (OOD) detection is concerned with identifying data points that do not belong to the same distribution as the model's training data. For the safe deployment of predictive models in a real-world environment, it is critical…

We propose visual-inertial simultaneous localization and mapping that tightly couples sparse reprojection errors, inertial measurement unit pre-integrals, and relative pose factors with dense volumetric occupancy mapping. Hereby depth…

In this work, we train a network to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD…

In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning. In practice, treating the unknown space in optimistic or pessimistic…

Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging conditions such as on low-resolution images or when the image is…

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs). This limitation is one of the key challenges in the adoption of DNNs in high-assurance systems such as…

Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate…

When deploying deep learning technology in self-driving cars, deep neural networks are constantly exposed to domain shifts. These include, e.g., changes in weather conditions, time of day, and long-term temporal shift. In this work we…

Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable…

We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…

State estimation is required whenever we deal with high-dimensional dynamical systems, as the complete measurement is often unavailable. It is key to gaining insight, performing control or optimizing design tasks. Most deep learning-based…

Safe, socially compliant, and efficient navigation of low-speed autonomous vehicles (AVs) in pedestrian-rich environments necessitates considering pedestrians' future positions and interactions with the vehicle and others. Despite the…

Deep Learning models are easily disturbed by variations in the input images that were not seen during training, resulting in unpredictable behaviours. Such Out-of-Distribution (OOD) images represent a significant challenge in the context of…