Modern hierarchical vision transformers have added several vision-specif...
The landscape of image generation has been forever changed by open vocab...
We introduce Token Merging (ToMe), a simple method to increase the throu...
While transformers have begun to dominate many tasks in vision, applying...
With the preponderance of pretrained deep learning models available
off-...
Convolutional Neural Networks have been shown to be vulnerable to advers...
We introduce TIDE, a framework and associated toolbox for analyzing the
...
We present a simple, fully-convolutional model for real-time (>30 fps)
i...
We present a simple, fully-convolutional model for real-time instance
se...