Related papers: Out-of-Sample Extrapolation with Neuron Editing

Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised…

In this paper, we develop a novel transformer-based generative adversarial neural network called U-Transformer for generalised image outpainting problem. Different from most present image outpainting methods conducting horizontal…

Brain extraction and registration are important preprocessing steps in neuroimaging data analysis, where the goal is to extract the brain regions from MRI scans (i.e., extraction step) and align them with a target brain image (i.e.,…

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount…

Deep generative models like StyleGAN hold the promise of semantic image editing: modifying images by their content, rather than their pixel values. Unfortunately, working with arbitrary images requires inverting the StyleGAN generator,…

Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images. However, how to steer the generation process of a well-trained GAN model and customize the output image is much less explored. It has been…

Generative adversarial networks achieve great performance in photorealistic image synthesis in various domains, including human images. However, they usually employ latent vectors that encode the sampled outputs globally. This does not…

Generative adversarial networks (GANs) have recently found applications in image editing. However, most GAN based image editing methods often require large scale datasets with semantic segmentation annotations for training, only provide…

Given the importance of nuclear mass predictions, numerous models have been developed to extrapolate the measured data into unknown regions. While neural networks -- the core of modern artificial intelligence -- have been recently suggested…

Hybrid optical neural networks (HONNs) offload some electronic computation to optical preprocessors to achieve low-power and fast training and inference phases in machine learning tasks. Our contribution to the development of HONNs is a…

Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN…

Graph Neural Network (GNN) research has produced strategies to modify a graph's edges using gradients from a trained GNN, with the goal of network design. However, the factors which govern gradient-based editing are understudied, obscuring…

State-of-the-art techniques in Generative Adversarial Networks (GANs) have shown remarkable success in image-to-image translation from peer domain X to domain Y using paired image data. However, obtaining abundant paired data is a…

Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters on domain-specific and task-specific benchmarks,…

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression…

Generative Adversarial Networks (GANs) typically learn a distribution of images in a large image dataset, and are then able to generate new images from this distribution. However, each natural image has its own internal statistics, captured…

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

Unsupervised image translation aims to learn the transformation from a source domain to another target domain given unpaired training data. Several state-of-the-art works have yielded impressive results in the GANs-based unsupervised…

We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. Differently from prior works, we solve this problem by learning a conditional probability…