With the advent of deep learning application on edge devices, researcher...
Generative models based on denoising diffusion techniques have led to an...
Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled targe...
In reinforcement learning, state representations are used to tractably d...
Recent work has shown that Neural Ordinary Differential Equations (ODEs)...
We propose a simple post hoc calibration method to estimate the
confiden...
Face recognition models suffer from bias: for example, the probability o...
Deep neural networks are vulnerable to adversarial perturbations: small
...
In this article we consider the problem of finding the visibility set fr...
Adversarial training is an effective method for improving robustness to
...
In this paper, we propose an implicit gradient descent algorithm for the...
We propose a new algorithm called Parle for parallel training of deep
ne...