Related papers: Style Quantization for Data-Efficient GAN Training

Generative Adversarial Networks (GAN) have been widely investigated for image synthesis based on their powerful representation learning ability. In this work, we explore the StyleGAN and its application of synthetic food image generation.…

Image stylization aims at applying a reference style to arbitrary input images. A common scenario is one-shot stylization, where only one example is available for each reference style. Recent approaches for one-shot stylization such as…

Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training. Existing approaches mitigate the overfitting by employing data augmentations, model regularization, or attention…

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Quantization is an effective way to reduce the memory cost of large-scale model training. However, most existing methods adopt fixed-precision policies, which ignore the fact that optimizer-state distributions vary significantly across…

Deep neural networks have achieved state-of-the-art accuracies in a wide range of computer vision, speech recognition, and machine translation tasks. However the limits of memory bandwidth and computational power constrain the range of…

Neural image compression has been shown to outperform traditional image codecs in terms of rate-distortion performance. However, quantization introduces errors in the compression process, which can degrade the quality of the compressed…

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood. To get deeper…

The inverse design of metasurfaces poses a considerable challenge because of the intricate interdependencies that exist between structural characteristics and electromagnetic responses. Traditional optimization methods require significant…

Approaches for improving generative adversarial networks (GANs) training under a few samples have been explored for natural images. However, these methods have limited effectiveness for synthetic aperture radar (SAR) images, as they do not…

Data-free quantization aims to achieve model quantization without accessing any authentic sample. It is significant in an application-oriented context involving data privacy. Converting noise vectors into synthetic samples through a…

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the…

Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their critic (discriminator) network during training. In this paper, we analyze the popular spectral normalization scheme, find a…

Generative adversarial networks (GANs), e.g., StyleGAN2, play a vital role in various image generation and synthesis tasks, yet their notoriously high computational cost hinders their efficient deployment on edge devices. Directly applying…

Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into…

Continuous path keyboard input has higher inherent ambiguity than standard tapping, because the path trace may exhibit not only local overshoots/undershoots (as in tapping) but also, depending on the user, substantial mid-path excursions.…

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of…

In recent years, Generative Adversarial Networks (GANs) have produced significantly improved results in speech enhancement (SE) tasks. They are difficult to train, however. In this work, we introduce several improvements to the GAN training…

To improve the stability of GAN training we need to understand why they can produce realistic samples. Presently, this is attributed to properties of the divergence obtained under an optimal discriminator. This argument has a fundamental…

Recently, Generative Adversarial Networks (GANs) have been successfully scaled to billion-scale large text-to-image datasets. However, training such models entails a high training cost, limiting some applications and research usage. To…