Related papers: Robust Uncertainty Estimation under Distribution S…
The ability of a deep learning network to distinguish between in-distribution (ID) and out-of-distribution (OOD) inputs is crucial for ensuring the reliability and trustworthiness of AI systems. Existing OOD detection methods often involve…
Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-distribution (OOD) data and adversarial examples. These represent distinct forms of distributional shifts that can significantly impact DNNs' reliability…
We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test…
Distribution shifts introduce uncertainty that undermines the robustness and generalization capabilities of machine learning models. While conventional wisdom suggests that learning causal-invariant representations enhances robustness to…
Despite the recent improvements in overall accuracy, deep learning systems still exhibit low levels of robustness. Detecting possible failures is critical for a successful clinical integration of these systems, where each data point…
Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging. The foundational models for vision and language, pre-trained on extensive…
The issue of disagreements amongst human experts is a ubiquitous one in both machine learning and medicine. In medicine, this often corresponds to doctor disagreements on a patient diagnosis. In this work, we show that machine learning…
Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essential. Output-based heuristics are cheap but brittle, while probing internal representations is effective yet high-dimensional and…
Predictive uncertainty estimation is an essential next step for the reliable deployment of deep object detectors in safety-critical tasks. In this work, we focus on estimating predictive distributions for bounding box regression output with…
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood…
In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may…
Accurately estimating uncertainties in neural network predictions is of great importance in building trusted DNNs-based models, and there is an increasing interest in providing accurate uncertainty estimation on many tasks, such as security…
Deployed machine learning models are confronted with the problem of changing data over time, a phenomenon also called concept drift. While existing approaches of concept drift detection already show convincing results, they require true…
Estimating uncertainty from deep neural networks is a widely used approach for detecting out-of-distribution (OoD) samples, which typically exhibit high predictive uncertainty. However, conventional methods such as Monte Carlo (MC) Dropout…
Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, together, can produce predictive distributions. In particular,…
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying…
Out-Of-Distribution (OOD) detection has received broad attention over the years, aiming to ensure the reliability and safety of deep neural networks (DNNs) in real-world scenarios by rejecting incorrect predictions. However, we notice a…
Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of…
In occluded person re-identification(ReID), severe occlusions lead to a significant amount of irrelevant information that hinders the accurate identification of individuals. These irrelevant cues primarily stem from background interference…
Deep neural networks (DNNs) are often constructed under the closed-world assumption, which may fail to generalize to the out-of-distribution (OOD) data. This leads to DNNs producing overconfident wrong predictions and can result in…