Do different neural networks, trained for various vision tasks, share so...
Test-time training adapts to a new test distribution on the fly by optim...
How does one adapt a pre-trained visual model to novel downstream tasks
...
We introduce MyStyle, a personalized deep generative prior trained with ...
We leverage deep features extracted from a pre-trained Vision Transforme...
Using only a model that was trained to predict where people look at imag...
Image classification models can depend on multiple different semantic
at...
Many seemingly unrelated computer vision tasks can be viewed as a specia...