3 papers
cs.CV2023
Semantic Generative Augmentations for Few-Shot Counting
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works sho…
cs.CV2023
Wasserstein Loss for Semantic Editing in the Latent Space of GANs
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
The latent space of GANs contains rich semantics reflecting the training data. Different methods propose to learn edits in latent space corresponding to semantic attributes, thus a…
cs.LG2021
Multi-Attribute Balanced Sampling for Disentangled GAN Controls
Perla Doubinsky, Nicolas Audebert, Michel Crucianu +1
Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered co…