Model-based deep learning
Signal processing, communications, and control have traditionally relied on classical
statistical modeling techniques. Such model-based methods utilize mathematical …
statistical modeling techniques. Such model-based methods utilize mathematical …
Focal frequency loss for image reconstruction and synthesis
Image reconstruction and synthesis have witnessed remarkable progress thanks to the
development of generative models. Nonetheless, gaps could still exist between the real and …
development of generative models. Nonetheless, gaps could still exist between the real and …
Melgan: Generative adversarial networks for conditional waveform synthesis
Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating
coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is …
coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is …
Semantic image synthesis with spatially-adaptive normalization
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing
photorealistic images given an input semantic layout. Previous methods directly feed the …
photorealistic images given an input semantic layout. Previous methods directly feed the …
Few-shot unsupervised image-to-image translation
Unsupervised image-to-image translation methods learn to map images in a given class to
an analogous image in a different class, drawing on unstructured (non-registered) datasets …
an analogous image in a different class, drawing on unstructured (non-registered) datasets …
Large scale adversarial representation learning
J Donahue, K Simonyan - Advances in neural information …, 2019 - proceedings.neurips.cc
Adversarially trained generative models (GANs) have recently achieved compelling image
synthesis results. But despite early successes in using GANs for unsupervised …
synthesis results. But despite early successes in using GANs for unsupervised …
High-resolution virtual try-on with misalignment and occlusion-handled conditions
Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing
item. To solve the task, the existing methods warp the clothing item to fit the person's body …
item. To solve the task, the existing methods warp the clothing item to fit the person's body …
Towards faster and stabilized gan training for high-fidelity few-shot image synthesis
Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires
large-scale GPU-clusters and a vast number of training images. In this paper, we study the …
large-scale GPU-clusters and a vast number of training images. In this paper, we study the …
[引用][C] Large Scale GAN Training for High Fidelity Natural Image Synthesis
A Brock - arXiv preprint arXiv:1809.11096, 2018
An overview of deep semi-supervised learning
Deep neural networks demonstrated their ability to provide remarkable performances on a
wide range of supervised learning tasks (eg, image classification) when trained on extensive …
wide range of supervised learning tasks (eg, image classification) when trained on extensive …