no code implementations • 8 May 2024 • Jonas Kohler, Albert Pumarola, Edgar Schönfeld, Artsiom Sanakoyeu, Roshan Sumbaly, Peter Vajda, Ali Thabet
Diffusion models are a powerful generative framework, but come with expensive inference.
no code implementations • 2 Dec 2022 • Edgar Schönfeld, Julio Borges, Vadim Sushko, Bernt Schiele, Anna Khoreva
Prior work has extensively studied the latent space structure of GANs for unconditional image synthesis, enabling global editing of generated images by the unsupervised discovery of interpretable latent directions.
1 code implementation • ICLR 2021 • Vadim Sushko, Edgar Schönfeld, Dan Zhang, Juergen Gall, Bernt Schiele, Anna Khoreva
By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, we are able to synthesize images of higher fidelity with better alignment to their input label maps, making the use of the perceptual loss superfluous.
3 code implementations • 28 Feb 2020 • Edgar Schönfeld, Bernt Schiele, Anna Khoreva
The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics, enabling the generator to synthesize images with varying structure, appearance and levels of detail, maintaining global and local realism.
Ranked #1 on Image Generation on CelebA 128x128
no code implementations • ICLR Workshop LLD 2019 • Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
While following the same direction, we also take artificial feature generation one step further and propose a model where a shared latent space of image features and class embeddings is learned by aligned variational autoencoders, for the purpose of generating latent features to train a softmax classifier.
2 code implementations • 5 Dec 2018 • Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.
Ranked #2 on Generalized Few-Shot Learning on AwA2