Search Results for author:
Found 3 papers, 2 papers with code
Customizing Text-to-Image Models with a Single Image Pair
Both qualitative and quantitative experiments show that our method can effectively learn style while avoiding overfitting to image content, highlighting the potential of modeling such stylistic differences from a single image pair.
Efficiently Learning the Graph for Semi-supervised Learning
We further show how to approximately learn the best graphs from the sparse families efficiently using the conjugate gradient method.
A Systematic Study of Bias Amplification
To enable this study, we design a simple image-classification problem in which we can tightly control (synthetic) biases.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
