234 citations · 374 across the 9 of their papers we have counts for
16 papers
Co-training Submodels for Visual Recognition
Hugo Touvron, Matthieu Cord, Maxime Oquab +3
We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we…
Unifying conditional and unconditional semantic image synthesis with OCO-GAN
Marlène Careil, Stéphane Lathuilière, Camille Couprie +1
Generative image models have been extensively studied in recent years. In the unconditional setting, they model the marginal distribution from unlabelled images. To allow for more…
DiffEdit: Diffusion-based semantic image editing with mask guidance
Guillaume Couairon, Jakob Verbeek, Holger Schwenk +1
Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we prop…
Three things everyone should know about Vision Transformers
Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby +2
After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks…
FlexIT: Towards Flexible Semantic Image Translation
Guillaume Couairon, Asya Grechka, Jakob Verbeek +2
Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains su…
Instance-Conditioned GAN
Arantxa Casanova, Marlène Careil, Jakob Verbeek +2
Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as Image…