Search Results for author:
Found 4 papers, 2 papers with code
Structural Similarity: When to Use Deep Generative Models on Imbalanced Image Dataset Augmentation
Our experiments on imbalanced image dataset classification show that, the validation accuracy improvement with such re-balancing method is related to the image similarity between different classes.
When do GANs replicate? On the choice of dataset size
With empirical evidence from BigGAN and StyleGAN2, on datasets CelebA, Flower and LSUN-bedroom, we show that dataset size and its complexity play an important role in GANs replication and perceptual quality of the generated images.
Leveraging The Topological Consistencies of Learning in Deep Neural Networks
Our newly developed practical topological characterization of DNNs allows for an additional set of applications.
Diamond in the rough: Improving image realism by traversing the GAN latent space
Leveraging the learned structure of the latent space, we find moving in this direction corrects many image artifacts and brings the image into greater realism.
