Related papers: Guided Uncertainty Learning Using a Post-Hoc Evide…
Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is…
Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. Recently proposed evidential neural networks explicitly account for different uncertainties by treating the network's outputs as evidence to…
Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes…
We evaluate two different methods for the integration of prediction uncertainty into diagnostic image classifiers to increase patient safety in deep learning. In the first method, Monte Carlo sampling is applied with dropout at test time to…
Deep learning has revolutionized modern data science. However, how to accurately quantify the uncertainty of predictions from large-scale deep neural networks (DNNs) remains an unresolved issue. To address this issue, we introduce a novel…
Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…
Adversarial distillation (AD) is a knowledge distillation technique that facilitates the transfer of robustness from teacher deep neural network (DNN) models to lightweight target (student) DNN models, enabling the target models to perform…
Pre-trained robot policies serve as the foundation of many validated robotic systems, which encapsulate extensive embodied knowledge. However, they often lack the semantic awareness characteristic of foundation models, and replacing them…
We propose a general way to integrate procedural knowledge of a domain into deep learning models. We apply it to the case of video prediction, building on top of object-centric deep models and show that this leads to a better performance…
A reliable uncertainty estimation method is the foundation of many modern out-of-distribution (OOD) detectors, which are critical for safe deployments of deep learning models in the open world. In this work, we propose TULiP, a…
Learning Path Recommendation (LPR) is critical for personalized education, yet current methods often fail to account for historical interaction uncertainty (e.g., lucky guesses or accidental slips) and lack adaptability to diverse learning…
Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks. Despite its popularity, its theoretical foundations…
With the rapid advancement in the performance of deep neural networks (DNNs), there has been significant interest in deploying and incorporating artificial intelligence (AI) systems into real-world scenarios. However, many DNNs lack the…
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution moreover correlates with a model's epistemic uncertainty,…
Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…
In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under perturbations to the…
In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…
Estimating how well a machine learning model performs during inference is critical in a variety of scenarios (for example, to quantify uncertainty, or to choose from a library of available models). However, the standard accuracy estimate of…
One of the bottlenecks in robotic intelligence is the instability of neural network models, which, unlike control models, lack a well-defined convergence domain and stability. This leads to risks when applying intelligence in the physical…