Predicting Token Impact Towards Efficient Vision Transformer

Predicting Token Impact Towards Efficient Vision Transformer

24 May 2023

ArXiv (abs)PDF HTML

Papers citing "Predicting Token Impact Towards Efficient Vision Transformer"

15 / 15 papers shown

Title
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer Wang Zeng Sheng Jin Wentao Liu Chao Qian Ping Luo Ouyang Wanli Xiaogang Wang ViT 70 126 0 19 Apr 2022
Stratified Transformer for 3D Point Cloud Segmentation Xin Lai Jianhui Liu Li Jiang Liwei Wang Hengshuang Zhao Shu Liu Xiaojuan Qi Jiaya Jia 3DPC ViT 114 274 0 28 Mar 2022
Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention Sitong Wu Tianyi Wu Hao Hao Tan G. Guo ViT 56 71 0 28 Dec 2021
AdaViT: Adaptive Tokens for Efficient Vision Transformer Hongxu Yin Arash Vahdat J. Álvarez Arun Mallya Jan Kautz Pavlo Molchanov ViT 107 340 0 14 Dec 2021
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows Xiaoyi Dong Jianmin Bao Dongdong Chen Weiming Zhang Nenghai Yu Lu Yuan Dong Chen B. Guo ViT 152 984 0 01 Jul 2021
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Yongming Rao Wenliang Zhao Benlin Liu Jiwen Lu Jie Zhou Cho-Jui Hsieh ViT 90 699 0 03 Jun 2021
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Enze Xie Wenhai Wang Zhiding Yu Anima Anandkumar J. Álvarez Ping Luo ViT 306 5,051 0 31 May 2021
Scaling Local Self-Attention for Parameter Efficient Visual Backbones Ashish Vaswani Prajit Ramachandran A. Srinivas Niki Parmar Blake A. Hechtman Jonathon Shlens 92 403 0 23 Mar 2021
Generative Adversarial Transformers Drew A. Hudson C. L. Zitnick ViT 74 181 0 01 Mar 2021
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao ViT 530 3,724 0 24 Feb 2021
Is Space-Time Attention All You Need for Video Understanding? Gedas Bertasius Heng Wang Lorenzo Torresani ViT 389 2,061 0 09 Feb 2021
Rethinking Attention with Performers K. Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane ... Afroz Mohiuddin Lukasz Kaiser David Belanger Lucy J. Colwell Adrian Weller 186 1,597 0 30 Sep 2020
BERT Loses Patience: Fast and Robust Inference with Early Exit Wangchunshu Zhou Canwen Xu Tao Ge Julian McAuley Ke Xu Furu Wei 47 341 0 07 Jun 2020
End-to-End Object Detection with Transformers Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov Sergey Zagoruyko ViT 3DV PINN 421 13,048 0 26 May 2020
Channel Pruning for Accelerating Very Deep Neural Networks Yihui He Xiangyu Zhang Jian Sun 204 2,525 0 19 Jul 2017