138 citations · 373 across the 23 of their papers we have counts for
23 papers
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Lijiang Li, Huixia Li, Xiawu Zheng +7
Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such t…
UGC: Unified GAN Compression for Efficient Image-to-Image Translation
Yuxi Ren, Jie Wu, Peng Zhang +6
Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on pond…
PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
Li Chen, Mengyi Zhao, Yiheng Liu +8
Personalized text-to-image generation has emerged as a powerful and sought-after tool, empowering users to create customized images based on their specific concepts and prompts. Ho…
DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection
Manlin Zhang, Jie Wu, Yuxi Ren +7
Data is the cornerstone of deep learning. This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection. Existing methods for scalin…
DLIP: Distilling Language-Image Pre-training
Huafeng Kuang, Jie Wu, Xiawu Zheng +5
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distilla…
AlignDet: Aligning Pre-training and Fine-tuning in Object Detection
Ming Li, Jie Wu, Xionghui Wang +6
The paradigm of large-scale pre-training followed by downstream fine-tuning has been widely employed in various object detection algorithms. In this paper, we reveal discrepancies…
AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose
Huichao Zhang, Bowen Chen, Hao Yang +7
Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and text…
HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation
Zuyan Liu, Gaojie Lin, Congyi Wang +2
With an enormous number of hand images generated over time, unleashing pose knowledge from unlabeled images for supervised hand mesh estimation is an emerging yet challenging topic…
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
Shizun Wang, Weihong Zeng, Xu Wang +7
The creation of a parameterized stylized character involves careful selection of numerous parameters, also known as the "avatar vectors" that can be interpreted by the avatar engin…
Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation
Jie Qin, Jie Wu, Ming Li +3
Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solu…
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…
Team PKU-WICT-MIPL PIC Makeup Temporal Video Grounding Challenge 2022 Technical Report
Minghang Zheng, Dejie Yang, Zhongjie Ye +3
In this technical report, we briefly introduce the solutions of our team `PKU-WICT-MIPL' for the PIC Makeup Temporal Video Grounding (MTVG) Challenge in ACM-MM 2022. Given an untri…
Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation
Ming Li, Jie Wu, Jinhang Cai +6
Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-…
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…
Dressing in the Wild by Watching Dance Videos
Xin Dong, Fuwei Zhao, Zhenyu Xie +6
While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild image…
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…
ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer
Rui Yang, Hailong Ma, Jie Wu +4
The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented gener…
Fast Convergence of DETR with Spatially Modulated Co-Attention
Peng Gao, Minghang Zheng, Xiaogang Wang +2
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection f…
Fast Convergence of DETR with Spatially Modulated Co-Attention
Peng Gao, Minghang Zheng, Xiaogang Wang +2
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection f…
End-to-End Object Detection with Adaptive Clustering Transformer
Minghang Zheng, Peng Gao, Renrui Zhang +4
End-to-end Object Detection with Transformer (DETR)proposes to perform object detection with Transformer and achieve comparable performance with two-stage object detection like Fas…
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…
Identify Equivalent Frames
Xuemei Chen, Yang Chu, Min Zheng
A frame is an overcomplete set that can represent vectors(signals) faithfully and stably. Two frames are equivalent if signals can be essentially represented in the same way, which…