The pre-training and fine-tuning paradigm has contributed to a number of...
This work introduces the RevSilo, the first reversible module for
bidire...
Recently many first and second order variants of SGD have been proposed ...
We propose combining memory saving techniques with traditional U-Net
arc...
We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm ...
In image classification, visual separability between different object
ca...
We identify a novel instance of the background subtraction problem that
...
Kernel approximation using randomized feature maps has recently gained a...