C Yu, T Chen, Z Gan, J Fan - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …
D Saxena, J Cao, J Xu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …
S Li, J Wu, X Xiao, F Chao… - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …
F Feng, J Wang, X Geng - arXiv preprint arXiv:2401.08139, 2024 - arxiv.org
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 …
BK Kim, S Choi, H Park - arXiv preprint arXiv:2206.14658, 2022 - arxiv.org
Pruning effectively compresses overparameterized models. Despite the success of pruning methods for discriminative models, applying them for generative models has been relatively …
NA Shah, G Bharaj - arXiv preprint arXiv:2203.10363, 2022 - arxiv.org
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 …
S John, A Danti - Annals of Emerging Technologies in Computing …, 2024 - aetic.theiaer.org
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 …