@cssastry.bsky.social
Excited to present our #NeurIPS2024 paper on synthetic augmentations with diffusion models! Stop by for discussions if any of the following topics are of interest: covariate-shift robustness, OOD detection, test-time augmentation, synthetic data, perceptually aligned gradients, classifier-guidance!
When can we use generator G, trained on a dataset X, to produce new data X', s.t. training S on X' outperforms training S on X? (see great discussion & articulation of this Q: x.com/phillip_isol... ).
@cssastry.bsky.social will present work on this on Thurs 11am-2pm, Poster 1804 #NeurIPS2024 :
1/n
@cssastry.bsky.social will present work on this on Thurs 11am-2pm, Poster 1804 #NeurIPS2024 :
1/n
December 12, 2024 at 4:55 PM
Excited to present our #NeurIPS2024 paper on synthetic augmentations with diffusion models! Stop by for discussions if any of the following topics are of interest: covariate-shift robustness, OOD detection, test-time augmentation, synthetic data, perceptually aligned gradients, classifier-guidance!