Related papers: CSG0: Continual Urban Scene Generation with Zero F…
Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…
Image generation has rapidly evolved in recent years. Modern architectures for adversarial training allow to generate even high resolution images with remarkable quality. At the same time, more and more effort is dedicated towards…
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a comprehensive comparison and analysis of limitations remains…
Generative adversarial networks (GANs) while being very versatile in realistic image synthesis, still are sensitive to the input distribution. Given a set of data that has an imbalance in the distribution, the networks are susceptible to…
Generating time series data using Generative Adversarial Networks (GANs) presents several prevalent challenges, such as slow convergence, information loss in embedding spaces, instability, and performance variability depending on the series…
The generative adversarial network (GAN) framework has emerged as a powerful tool for various image and video synthesis tasks, allowing the synthesis of visual content in an unconditional or input-conditional manner. It has enabled the…
A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…
Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…
Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of still images, as well as the learning of temporal correlations. However, few works manage to combine these two interesting capabilities for…
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…
Learning novel concepts, remembering previous knowledge, and adapting it to future tasks occur simultaneously throughout a human's lifetime. To model such comprehensive abilities, continual zero-shot learning (CZSL) has recently been…
Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally…
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…
We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a…
Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional…
Many recent methods of zero-shot learning (ZSL) attempt to utilize generative model to generate the unseen visual samples from semantic descriptions and random noise. Therefore, the ZSL problem becomes a traditional supervised…
Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work…
We revisit human motion synthesis, a task useful in various real world applications, in this paper. Whereas a number of methods have been developed previously for this task, they are often limited in two aspects: focusing on the poses while…
Scene graphs provide a rich, structured representation of a scene by encoding the entities (objects) and their spatial relationships in a graphical format. This representation has proven useful in several tasks, such as question answering,…
The performance of face recognition (FR) systems applied in video surveillance has been shown to improve when the design data is augmented through synthetic face generation. This is true, for instance, with pair-wise matchers (e.g., deep…