Class-incremental continual learning is a core step towards developing
a...
Deep learning-based models are developed to automatically detect if a re...
Despite the remarkable performance, Deep Neural Networks (DNNs) behave a...
Existing adversarially trained models typically perform inference on tes...
Learning semantically meaningful features is important for Deep Neural
N...
Among existing uncertainty estimation approaches, Dirichlet Prior Networ...
Existing defenses against adversarial attacks are typically tailored to ...
Gaussian distributions are commonly used as a key building block in many...
User opinions expressed in the form of ratings can influence an individu...