Related papers: Post-training Model Quantization Using GANs for Sy…

Deep generative frameworks including GANs and normalizing flow models have proven successful at filling in missing values in partially observed data samples by effectively learning -- either explicitly or implicitly -- complex,…

Synthetic data can be used in various applications, such as correcting bias datasets or replacing scarce original data for simulation purposes. Generative Adversarial Networks (GANs) are considered state-of-the-art for developing generative…

Post-training quantization (PTQ) is a neural network compression technique that converts a full-precision model into a quantized model using lower-precision data types. Although it can help reduce the size and computational cost of deep…

The availability of training data is one of the main limitations in deep learning applications for medical imaging. Data augmentation is a popular approach to overcome this problem. A new approach is a Machine Learning based augmentation,…

Generative adversarial networks (GANs) have recently become a popular data augmentation technique used by machine learning practitioners. However, they have been shown to suffer from the so-called mode collapse failure mode, which makes…

Generative Adversarial Networks (GANs) have been extremely successful in various application domains such as computer vision, medicine, and natural language processing. Moreover, transforming an object or person to a desired shape become a…

We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to…

Generative adversarial networks (GANs) have shown great success in applications such as image generation and inpainting. However, they typically require large datasets, which are often not available, especially in the context of prediction…

To efficiently run DNNs on the edge/cloud, many new DNN inference accelerators are being designed and deployed frequently. To enhance the resource efficiency of DNNs, model quantization is a widely-used approach. However, different…

Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation. However, standard DA produces synthetic data for augmentation with limited…

Since technology is advancing so quickly in the modern era of information, data is becoming an essential resource in many fields. Correct data collection, organization, and analysis make it a potent tool for successful decision-making,…

A generative adversarial network (GAN) has been a representative backbone model in generative artificial intelligence (AI) because of its powerful performance in capturing intricate data-generating processes. However, the GAN training is…

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

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…

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain…