Efficient spatially sparse inference for conditional gans and diffusion models

M Li, J Lin, C Meng, S Ermon… - Advances in neural …, 2022 - proceedings.neurips.cc
During image editing, existing deep generative models tend to re-synthesize the entire
output from scratch, including the unedited regions. This leads to a significant waste of …

Snapfusion: Text-to-image diffusion model on mobile devices within two seconds

Y Li, H Wang, Q **, J Hu… - Advances in …, 2023 - proceedings.neurips.cc
Text-to-image diffusion models can create stunning images from natural language
descriptions that rival the work of professional artists and photographers. However, these …

Rethinking vision transformers for mobilenet size and speed

Y Li, J Hu, Y Wen, G Evangelidis… - Proceedings of the …, 2023 - openaccess.thecvf.com
With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to
optimize the performance and complexity of ViTs to enable efficient deployment on mobile …

Gan compression: Efficient architectures for interactive conditional gans

M Li, J Lin, Y Ding, Z Liu, JY Zhu… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract Conditional Generative Adversarial Networks (cGANs) have enabled controllable
image synthesis for many computer vision and graphics applications. However, recent …

Wavelet knowledge distillation: Towards efficient image-to-image translation

L Zhang, X Chen, X Tu, P Wan… - Proceedings of the …, 2022 - openaccess.thecvf.com
Remarkable achievements have been attained with Generative Adversarial Networks
(GANs) in image-to-image translation. However, due to a tremendous amount of parameters …

On architectural compression of text-to-image diffusion models

BK Kim, HK Song, T Castells, S Choi - 2023 - openreview.net
Exceptional text-to-image (T2I) generation results of Stable Diffusion models (SDMs) come
with substantial computational demands. To resolve this issue, recent research on efficient …

Pointdistiller: Structured knowledge distillation towards efficient and compact 3d detection

L Zhang, R Dong, HS Tai, K Ma - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The remarkable breakthroughs in point cloud representation learning have boosted their
usage in real-world applications such as self-driving cars and virtual reality. However, these …
Z Xu, Z Hong, C Ding, Z Zhu, J Han, J Liu… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Advanced face swap** methods have achieved appealing results. However, most of these
methods have many parameters and computations, which makes it challenging to apply …

Pruning-as-search: Efficient neural architecture search via channel pruning and structural reparameterization

Y Li, P Zhao, G Yuan, X Lin, Y Wang… - arxiv preprint arxiv …, 2022 - arxiv.org
Neural architecture search (NAS) and network pruning are widely studied efficient AI
techniques, but not yet perfect. NAS performs exhaustive candidate architecture search …