Related papers: Calibration of Deep Learning Classification Models…

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…

Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model calibration techniques mitigate the problem of…

Resting state fMRI is an imaging modality which reveals brain activity localization through signal changes, in what is known as Resting State Networks (RSNs). This technique is gaining popularity in neurosurgical pre-planning to visualize…

Recently, deep neural networks have become to be used in a variety of applications. While the accuracy of deep neural networks is increasing, the confidence score, which indicates the reliability of the prediction results, is becoming more…

Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as…

Deep clustering has exhibited remarkable performance; however, the over confidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been over looked…

Hyperscanning with functional near-infrared spectroscopy (fNIRS) is an emerging neuroimaging application that measures the nuanced neural signatures underlying social interactions. Researchers have assessed the effect of sex and task type…

Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly…

Magnetic Resonance Imaging (MRI) of the brain has benefited from deep learning (DL) to alleviate the burden on radiologists and MR technologists, and improve throughput. The easy accessibility of DL tools have resulted in the rapid increase…

Functional Near-Infrared Spectroscopy (fNIRS) is a non-invasive, real-time method for monitoring brain activity by measuring hemodynamic responses in the cerebral cortex. However, existing systems are expensive, bulky, and limited to…

Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…

While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these…

Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar.In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of…

Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…

Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a function whose values correctly reflect underlying label probabilities. Calibration…

Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. However, although the task of confidence calibration has been…

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision…

The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains,…

Ensuring that predicted probabilities align with observed frequencies is critical in high-stakes domains such as clinical decision support, autonomous driving and financial risk assessment. Existing calibration methods typically apply a…