While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the ...
Abstract: Diffusion models are a powerful class of techniques in ML for generating realistic data, but they are highly prone to overfitting, especially with limited training data. While data ...
Abstract: Earth observation data have proven to be a valuable resource of quantitative information that is more consistent in time and space than traditional land-based surveys. Remote sensing plays a ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback