Related papers: Improved Consistency Regularization for GANs
Deep generative models, such as Generative Adversarial Networks (GANs), synthesize diverse high-fidelity data samples by estimating the underlying distribution of high dimensional data. Despite their success, GANs may disclose private…
Image generation with explicit condition or label generally works better than unconditional methods. In modern GAN frameworks, both generator and discriminator are formulated to model the conditional distribution of images given with…
Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…
Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve…
Generative Adversarial Networks (GAN) have attracted much research attention recently, leading to impressive results for natural image generation. However, to date little success was observed in using GAN generated images for improving…
Conditional GANs are widely used in translating an image from one category to another. Meaningful conditions to GANs provide greater flexibility and control over the nature of the target domain synthetic data. Existing conditional GANs…
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…
Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful…
Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization. However, existing training procedures are limited to images of low resolution (typically below 32x32), and…
Recent advancement in generative models have demonstrated remarkable performance across various data modalities. Beyond their typical use in data synthesis, these models play a crucial role in distribution matching tasks such as latent…
Recently, 3D GANs based on 3D Gaussian splatting have been proposed for high quality synthesis of human heads. However, existing methods stabilize training and enhance rendering quality from steep viewpoints by conditioning the random…
Although existing Quantization-Aware Training (QAT) methods intensively depend on knowledge distillation to guarantee performance, QAT still suffers from severe performance drop. The experiments have shown that vanilla quantization is…
The generator in the generative adversarial network (GAN) learns image generation in a coarse-to-fine manner in which earlier layers learn the overall structure of the image and the latter ones refine the details. To propagate the coarse…
Large annotated datasets are required to train segmentation networks. In medical imaging, it is often difficult, time consuming and expensive to create such datasets, and it may also be difficult to share these datasets with other…
New medical datasets are now more open to the public, allowing for better and more extensive research. Although prepared with the utmost care, new datasets might still be a source of spurious correlations that affect the learning process.…
Adversarial nets have proved to be powerful in various domains including generative modeling (GANs), transfer learning, and fairness. However, successfully training adversarial nets using first-order methods remains a major challenge.…
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real…
Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways. They often learn distributions with low…
Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different…
SCGAN adds a similarity constraint between generated images and conditions as a regularization term on generative adversarial networks. Similarity constraint works as a tutor to instruct the generator network to comprehend the difference of…