CvT: Introducing Convolutions to Vision Transformers

IEEE International Conference on Computer Vision (ICCV), 2021

29 March 2021

Lu Yuan

Lei Zhang

ViT

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)Github (227★)

Papers citing "CvT: Introducing Convolutions to Vision Transformers"

50 / 857 papers shown

Title
IA-RED $^2$ : Interpretability-Aware Redundancy Reduction for Vision Transformers Bowen Pan Yikang Shen Lezhi Li Zinan Lin Rogerio Feris A. Oliva VLM ViT 271 191 0 23 Jun 2021
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition Qibin Hou Zihang Jiang Li-xin Yuan Mingg-Ming Cheng Shuicheng Yan Jiashi Feng ViT MLLM 248 230 0 23 Jun 2021
P2T: Pyramid Pooling Transformer for Scene UnderstandingIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Yu-Huan Wu Yun-Hai Liu Xin Zhan Mingg-Ming Cheng ViT 458 281 0 22 Jun 2021
Encoder-Decoder Architectures for Clinically Relevant Coronary Artery SegmentationInternational Conference on Computational Advances in Bio and Medical Sciences (ICCABS), 2021 Joao Lourencco Silva M. Menezes T. Rodrigues B. Silva F. Pinto Arlindo L. Oliveira MedIm 179 22 0 21 Jun 2021
More than Encoder: Introducing Transformer Decoder to UpsampleIEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021 Yijiang Li Wentian Cai Ying Gao Chengming Li Xiping Hu ViT MedIm 165 71 0 20 Jun 2021
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers Andreas Steiner Alexander Kolesnikov Xiaohua Zhai Ross Wightman Jakob Uszkoreit Lucas Beyer ViT 315 759 0 18 Jun 2021
Efficient Self-supervised Vision Transformers for Representation LearningInternational Conference on Learning Representations (ICLR), 2021 Chunyuan Li Jianwei Yang Pengchuan Zhang Mei Gao Bin Xiao Xiyang Dai Lu Yuan Jianfeng Gao ViT 223 221 0 17 Jun 2021
S $^2$ -MLP: Spatial-Shift MLP Architecture for VisionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2021 Tan Yu Xu Li Yunfeng Cai Mingming Sun Ping Li 216 214 0 14 Jun 2021
Styleformer: Transformer based Generative Adversarial Networks with Style VectorComputer Vision and Pattern Recognition (CVPR), 2021 Jeeseung Park Younggeun Kim ViT 256 58 0 13 Jun 2021
MlTr: Multi-label Classification with TransformerIEEE International Conference on Multimedia and Expo (ICME), 2021 Xingyi Cheng Hezheng Lin Xiangyu Wu Fan Yang Dong Shen Zhongyuan Wang Nian Shi Honglin Liu ViT 119 53 0 11 Jun 2021
Transformed CNNs: recasting pre-trained convolutional layers with self-attention Stéphane dÁscoli Levent Sagun Giulio Biroli Ari S. Morcos ViT 70 7 0 10 Jun 2021
CAT: Cross Attention in Vision TransformerIEEE International Conference on Multimedia and Expo (ICME), 2021 Hezheng Lin Xingyi Cheng Xiangyu Wu Fan Yang Dong Shen Zhongyuan Wang Qing Song Wei Yuan ViT 148 250 0 10 Jun 2021
CoAtNet: Marrying Convolution and Attention for All Data SizesNeural Information Processing Systems (NeurIPS), 2021 Zihang Dai Hanxiao Liu Quoc V. Le Mingxing Tan ViT 382 1,433 0 09 Jun 2021
TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoising Dayang Wang Zhan Wu Hengyong Yu ViT MedIm 175 64 0 08 Jun 2021
On the Connection between Local Attention and Dynamic Depth-wise ConvolutionInternational Conference on Learning Representations (ICLR), 2021 Qi Han Zejia Fan Jingdong Sun Lei-huan Sun Ming-Ming Cheng Jiaying Liu Jingdong Wang ViT 272 131 0 08 Jun 2021
On Improving Adversarial Transferability of Vision TransformersInternational Conference on Learning Representations (ICLR), 2021 Muzammal Naseer Kanchana Ranasinghe Salman Khan Fahad Shahbaz Khan Fatih Porikli ViT 206 106 0 08 Jun 2021
Fully Transformer Networks for Semantic Image Segmentation Sitong Wu Tianyi Wu Fangjian Lin Sheng Tian Guodong Guo ViT 224 47 0 08 Jun 2021
Efficient Training of Visual Transformers with Small DatasetsNeural Information Processing Systems (NeurIPS), 2021 Yahui Liu E. Sangineto Wei Bi Andrii Zadaianchuk Bruno Lepri Marco De Nadai ViT 148 211 0 07 Jun 2021
Reveal of Vision Transformers Robustness against Adversarial Attacks Ahmed Aldahdooh W. Hamidouche Olivier Déforges ViT 177 67 0 07 Jun 2021
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer Zilong Huang Youcheng Ben Guozhong Luo Pei Cheng Gang Yu Bin-Bin Fu ViT 221 207 0 07 Jun 2021
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive BiasNeural Information Processing Systems (NeurIPS), 2021 Yufei Xu Qiming Zhang Jing Zhang Dacheng Tao ViT 329 386 0 07 Jun 2021
Vision Transformers with Hierarchical AttentionMachine Intelligence Research (MIR), 2021 Yun-Hai Liu Yu-Huan Wu Guolei Sun Le Zhang Ajad Chhatkuli Luc Van Gool ViT 159 65 0 06 Jun 2021
CAPE: Encoding Relative Positions with Continuous Augmented Positional EmbeddingsNeural Information Processing Systems (NeurIPS), 2021 Tatiana Likhomanenko Qiantong Xu Gabriel Synnaeve R. Collobert A. Rogozhnikov OOD ViT 266 68 0 06 Jun 2021
Uformer: A General U-Shaped Transformer for Image RestorationComputer Vision and Pattern Recognition (CVPR), 2021 Zhendong Wang Xiaodong Cun Jianmin Bao Wengang Zhou Jianzhuang Liu Houqiang Li ViT 447 1,814 0 06 Jun 2021
RegionViT: Regional-to-Local Attention for Vision TransformersInternational Conference on Learning Representations (ICLR), 2021 Chun-Fu Chen Yikang Shen Quanfu Fan ViT 366 224 0 04 Jun 2021
Glance-and-Gaze Vision TransformerNeural Information Processing Systems (NeurIPS), 2021 Qihang Yu Yingda Xia Yutong Bai Yongyi Lu Alan Yuille Wei Shen ViT 148 82 0 04 Jun 2021
X-volution: On the unification of convolution and self-attention Xuanhong Chen Hang Wang Bingbing Ni ViT 100 27 0 04 Jun 2021
Attention mechanisms and deep learning for machine vision: A survey of the state of the art A. M. Hafiz S. A. Parah R. A. Bhat 211 51 0 03 Jun 2021
SegFormer: Simple and Efficient Design for Semantic Segmentation with TransformersNeural Information Processing Systems (NeurIPS), 2021 Enze Xie Wenhai Wang Zhiding Yu Anima Anandkumar J. Álvarez Ping Luo ViT 1.1K 6,783 0 31 May 2021
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger TokensComputer Vision and Pattern Recognition (CVPR), 2021 Jiemin Fang Lingxi Xie Xinggang Wang Xiaopeng Zhang Wenyu Liu Qi Tian ViT 178 84 0 31 May 2021
Analogous to Evolutionary Algorithm: Designing a Unified Sequence ModelNeural Information Processing Systems (NeurIPS), 2021 Jiangning Zhang Chao Xu Jian Li Wenzhou Chen Yabiao Wang Ying Tai Shuo Chen Chengjie Wang Feiyue Huang Yong Liu 249 25 0 31 May 2021
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image RecognitionNeural Information Processing Systems (NeurIPS), 2021 Yulin Wang Rui Huang Qing Xiao Zeyi Huang Gao Huang ViT 242 230 0 31 May 2021
Dual-stream Network for Visual RecognitionNeural Information Processing Systems (NeurIPS), 2021 Mingyuan Mao Renrui Zhang Honghui Zheng Shiyang Feng Teli Ma Yan Peng Errui Ding Baochang Zhang Shumin Han ViT 187 77 0 31 May 2021
Less is More: Pay Less Attention in Vision TransformersAAAI Conference on Artificial Intelligence (AAAI), 2021 Zizheng Pan Bohan Zhuang Haoyu He Jing Liu Jianfei Cai ViT 277 101 0 29 May 2021
KVT: k-NN Attention for Boosting Vision TransformersEuropean Conference on Computer Vision (ECCV), 2021 Pichao Wang Qingsong Wen F. Wang Ming Lin Shuning Chang Hao Li Rong Jin ViT 225 128 0 28 May 2021
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingAAAI Conference on Artificial Intelligence (AAAI), 2021 Zizhao Zhang Han Zhang Long Zhao Ting Chen Sercan O. Arik Tomas Pfister ViT 257 201 0 26 May 2021
Pay Attention to MLPsNeural Information Processing Systems (NeurIPS), 2021 Hanxiao Liu Zihang Dai David R. So Quoc V. Le AI4CE 484 781 0 17 May 2021
Towards Robust Vision TransformerComputer Vision and Pattern Recognition (CVPR), 2021 Xiaofeng Mao Gege Qi YueFeng Chen Xiaodan Li Ranjie Duan Shaokai Ye Yuan He Hui Xue ViT 362 224 0 17 May 2021
Waste detection in Pomerania: non-profit project for detecting waste in environmentWaste Management (Waste Manag.), 2021 Sylwia Majchrowska Agnieszka Mikołajczyk M. Ferlin Zuzanna Klawikowska Marta A. Plantykow Arkadiusz Kwasigroch K. Majek 247 158 0 12 May 2021
Homogeneous vector bundles and $G$ -equivariant convolutional neural networksSampling Theory, Signal Processing, and Data Analysis (SAMPTA), 2021 J. Aronsson 183 26 0 12 May 2021
Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet Luke Melas-Kyriazi ViT 115 115 0 06 May 2021
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Meng-Hao Guo Zheng-Ning Liu Tai-Jiang Mu Shimin Hu 165 616 0 05 May 2021
Twins: Revisiting the Design of Spatial Attention in Vision TransformersNeural Information Processing Systems (NeurIPS), 2021 Xiangxiang Chu Zhi Tian Yuqing Wang Bo Zhang Haibing Ren Xiaolin K. Wei Huaxia Xia Chunhua Shen ViT 509 1,199 0 28 Apr 2021
Vision Transformers with Patch Diversification Chengyue Gong Dilin Wang Meng Li Vikas Chandra Qiang Liu ViT 209 67 0 26 Apr 2021
Visformer: The Vision-friendly TransformerIEEE International Conference on Computer Vision (ICCV), 2021 Zhengsu Chen Lingxi Xie Jianwei Niu Xuefeng Liu Longhui Wei Qi Tian ViT 459 266 0 26 Apr 2021
VidTr: Video Transformer Without ConvolutionsIEEE International Conference on Computer Vision (ICCV), 2021 Yanyi Zhang Xinyu Li Chunhui Liu Bing Shuai Yi Zhu Biagio Brattoli Hao Chen I. Marsic Joseph Tighe ViT 369 215 0 23 Apr 2021
All Tokens Matter: Token Labeling for Training Better Vision TransformersNeural Information Processing Systems (NeurIPS), 2021 Zihang Jiang Qibin Hou Li-xin Yuan Daquan Zhou Yujun Shi Xiaojie Jin Anran Wang Jiashi Feng ViT 325 236 0 22 Apr 2021
Escaping the Big Data Paradigm with Compact Transformers Ali Hassani Steven Walton Nikhil Shah Abulikemu Abuduweili Jiachen Li Humphrey Shi 473 533 0 12 Apr 2021
HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies Muhammad AbdurRafae OCL 46 1 0 08 Apr 2021
LeViT: a Vision Transformer in ConvNet's Clothing for Faster InferenceIEEE International Conference on Computer Vision (ICCV), 2021 Ben Graham Alaaeldin El-Nouby Hugo Touvron Pierre Stock Armand Joulin Edouard Grave Matthijs Douze ViT 282 932 0 02 Apr 2021