Our research aims to unify existing works' diverging opinions on how
arc...
Adversarial Training is the most effective approach for improving the
ro...
Class imbalance is a ubiquitous phenomenon occurring in real world data
...
With the shift towards on-device deep learning, ensuring a consistent
be...
Deep neural networks (DNNs) have been widely used for decision making,
p...
Existing research on making sense of deep neural networks often focuses ...
We tackle the problem of visual search under resource constraints. Exist...
Computer vision is playing an increasingly important role in automated
m...
The natural world often follows a long-tailed data distribution where on...
In recent years, significant attention has been devoted towards integrat...
We propose Cluster Pruning (CUP) for compressing and accelerating deep n...
In mainstream computer vision and machine learning, public datasets such...
Image-matched nonseparable wavelets can find potential use in many
appli...