Reliable confidence estimation for the predictions is important in many safety-critical
applications. However, modern deep neural networks are often overconfident for their …

Albeit revealing impressive predictive performance for several computer vision tasks, deep
neural networks (DNNs) are prone to making overconfident predictions. This limits the …

Network calibration aims to accurately estimate the level of confidences, which is particularly
important for employing deep neural networks in real-world systems. Recent approaches …

Modern visual recognition models often display overconfidence due to their reliance on
complex deep neural networks and one-hot target supervision, resulting in unreliable …

Recent studies have revealed that, beyond conventional accuracy, calibration should also
be considered for training modern deep neural networks. To address miscalibration during …

Despite the undeniable progress in visual recognition tasks fueled by deep neural networks,
there exists recent evidence showing that these models are poorly calibrated, resulting in …

Albeit achieving high predictive accuracy across many challenging computer vision
problems, recent studies suggest that deep neural networks (DNNs) tend to make …

Proper confidence calibration of deep neural networks is essential for reliable predictions in
safety-critical tasks. Miscalibration can lead to model over-confidence and/or under …

This paper addresses the critical issue of miscalibration in CLIP-based model adaptation,
particularly in the challenging scenario of out-of-distribution (OOD) samples, which has been …

We study the impact of different loss functions on lesion segmentation from medical images.
Although the Cross-Entropy (CE) loss is the most popular option when dealing with natural …