Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …

For semantic segmentation, label probabilities are often uncalibrated as they are typically
only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are …

Calibrating deep neural models plays an important role in building reliable, robust AI
systems in safety-critical applications. Recent work has shown that modern neural networks …

Hate speech moderation remains a challenging task for social media platforms. Human-AI
collaborative systems offer the potential to combine the strengths of humans' reliability and …

Despite impressive accuracy, deep neural networks are often miscalibrated and tend to
overly confident predictions. Recent techniques like temperature scaling (TS) and label …

Deep support vector data description (DeSVDD) is an emerging anomaly detection method
based on the deep learning methodology. However, few studies take the confidence of …

The vulnerability of deep neural networks to adversarial samples poses significant security
concerns. Previous empirical analyses have shown that increasing adversarial robustness …

Automatic classification of remote sensing images using machine learning techniques is
challenging due to the complex features of the images. The images are characterized by …

Technological and computational advances continuously drive forward the broad field of
deep learning. In recent years, the derivation of quantities describing theuncertainty in the …

With this work we tackle immunofluorescence classification in renal biopsy, employing state-
of-the-art Convolutional Neural Networks. In this setting, the aim of the probabilistic model is …