138 citations · 215 across the 9 of their papers we have counts for
10 papers
Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
Yanzuo Lu, Yuxi Ren, Xin Xia +6
Distribution Matching Distillation (DMD) is a promising score distillation technique that compresses pre-trained teacher diffusion models into efficient one-step or multi-step stud…
Training-free Diffusion Acceleration with Bottleneck Sampling
Ye Tian, Xin Xia, Yuxi Ren +6
Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This…
RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
Huiyang Shao, Xin Xia, Yuhong Yang +3
Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while ai…
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Yuxi Ren, Xin Xia, Yanzuo Lu +5
Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Mod…
VmambaIR: Visual State Space Model for Image Restoration
Yuan Shi, Bin Xia, Xiaoyu Jin +5
Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks…
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Jiashi Li, Xin Xia, Wei Li +6
Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realist…
MoCoViT: Mobile Convolutional Vision Transformer
Hailong Ma, Xin Xia, Xing Wang +3
Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mo…
TRT-ViT: TensorRT-oriented Vision Transformer
Xin Xia, Jiashi Li, Jie Wu +4
We revisit the existing excellent Transformers from the perspective of practical application. Most of them are not even as efficient as the basic ResNets series and deviate from th…
SepViT: Separable Vision Transformer
Wei Li, Xing Wang, Xin Xia +5
Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performan…
Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search
Xin Xia, Xuefeng Xiao, Xing Wang +1
Neural Architecture Search (NAS) has attracted growing interest. To reduce the search cost, recent work has explored weight sharing across models and made major progress in One-Sho…