Search Results for author:
Found 2 papers, 1 papers with code
Improved DDIM Sampling with Moment Matching Gaussian Mixtures
For example on ImageNet 256x256, using 10 sampling steps, we achieve a FID of 6. 94 and IS of 207. 85 with a GMM kernel compared to 10. 15 and 196. 73 respectively with a Gaussian kernel.
Probabilistic Attention for Interactive Segmentation
We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
