logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

PiT: Progressive diffusion transformer

delete2026-08-25
delete0
PRE
AI
J
Jiafu Wu
Y
Yabiao Wang
李健 封面图
李健 (Jian Li)
J
Jinlong Peng
Y
Yun Cao
C
Chengjie Wang
J
Jiangning Zhang
刘
刘勇 (Yong Liu) *
DOI：10.1016/j.patcog.2026.114732delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• DiT 不依赖长距离注意力，提出了静态窗口注意力。 • 引入了伪移位窗口注意力以增强高频信息。 • 我们首创了视觉生成中的 K 阶注意力概念。 • 逐步覆盖通道分配实现了有效的 K 阶注意力。 • PiT，一种新的视觉骨干网络，实现了 SOTA 性能，且比 DiT 快 2.46 倍。
Keyword:
Image generation
Diffusion transformer
Attention similarity

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

T
Tencent
学者数:
1.1K
论文数: 898
被引数: 5
Z
zhejiang university
学者数:
17.7W
论文数: 12.1W
被引数: 152
引用论文

引用论文

Masked-attention Mask Transformer for Universal Image Segmentation用于通用图像分割的Masked-注意掩模变压器
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errBowen Cheng; Ishan Misra; Alexander G. Schwing; Alexander Kirillov; Rohit Girdhar
err分享
err收藏
High-Resolution Image Synthesis with Latent Diffusion Models具有潜在扩散模型的高分辨率图像合成
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errRobin Rombach; Andreas Blattmann; Dominik Lorenz; Patrick Esser; Bjorn Ommer
err分享
err收藏
All are Worth Words: A ViT Backbone for Diffusion Models
err2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2023-06-01
err0
errOAAI
errFan Bao; Shen Nie; Kaiwen Xue; Yue Cao; Chongxuan Li; Hang Su; Jun Zhu
err分享
err收藏
Scalable Diffusion Models with Transformers
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
errOAAI
errWilliam Peebles; Saining Xie
err分享
err收藏
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
err2021 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2021-10-01
err0
errOAAI
errChun-Fu Richard Chen; Quanfu Fan; Rameswar Panda
err分享
err收藏
Masked Diffusion Transformer is a Strong Image Synthesizer
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
PREAI
errShanghua Gao; Pan Zhou; Ming-Ming Cheng; Shuicheng Yan
err分享
err收藏
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
err2021 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2021-10-01
err0
errOAAI
errLi Yuan; Yunpeng Chen; Tao Wang; Weihao Yu; Yujun Shi; Zihang Jiang; Francis E. H. Tay; Jiashi Feng; Shuicheng Yan
err分享
err收藏
U-DiTs: Downsample Tokens in U-Shaped Diffusion TransformersU-DiTs：U形扩散变换器中的下采样标记
errAdvances in Neural Information Processing Systems 37
IF0
err2024-01-01
err0
PREAI
errTian,Yuchuan; Tu,Zhijun; Chen,Hanting; Hu,Jie; Xu,Chao; Wang,Yunhe
err分享
err收藏
On Attention Redundancy: A Comprehensive Study
errProceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
IF0
err2021-01-01
err0
errOAAI
errYuchen Bian; Jiaji Huang; Xingyu Cai; Jiahong Yuan; Kenneth Church
err分享
err收藏
Pre-Trained Image Processing Transformer
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errHanting Chen; Yunhe Wang; Tianyu Guo; Chang Xu; Yiping Deng; Zhenhua Liu; Siwei Ma; Chunjing Xu; Chao Xu; Wen Gao
err分享
err收藏
学者 查看更多内容