As neural network model sizes have dramatically increased, so has the interest in various
techniques to reduce their parameter counts and accelerate their execution. An active area …

The transformer extends its success from the language to the vision domain. Because of the
numerous stacked self-attention and cross-attention blocks in the transformer, which involve …

Abstract Training Generative Adversarial Networks (GANs) on high-fidelity images usually
requires a vast number of training images. Recent research on GAN tickets reveals that …

Recently, a series of algorithms have been explored for GAN compression, which aims to
reduce tremendous computational overhead and memory usages when deploying GANs on …

Over the past few years, there has been growing interest in developing larger and deeper
neural networks, including deep generative models like generative adversarial networks …

Generative Adversarial Networks (GANs) have shown remarkable success in modeling
complex data distributions for image-to-image translation. Still, their high computational …

The pre-training paradigm fine-tunes the models trained on large-scale datasets to
downstream tasks with enhanced performance. It transfers all knowledge to downstream …

Pruning effectively compresses overparameterized models. Despite the success of pruning
methods for discriminative models, applying them for generative models has been relatively …

We present a novel algorithm to reduce tensor compute required by a conditional image
generation autoencoder without sacrificing quality of photo-realistic image generation. Our …

In the realm of deep learning, the prevalence of models with large number of parameters
poses a significant challenge for low computation device. Critical influence of model size …