Results 21 to 30 of about 1,683,190 (291)

Vision Transformers for Image Classification: A Comparative Survey

Technologies
Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures.
Yaoli Wang, Yaojun Deng, Yuanjin Zheng, Pratik Chattopadhyay, Lipo Wang   +4 more
doaj   +2 more sources

Transformers for Vision: A Survey on Innovative Methods for Computer Vision

IEEE Access
Transformers have emerged as a groundbreaking architecture in the field of computer vision, offering a compelling alternative to traditional convolutional neural networks (CNNs) by enabling the modeling of long-range dependencies and global context ...
Balamurugan Palanisamy, Vikas Hassija, Arpita Chatterjee, Arpita Mandal, Debanshi Chakraborty, Amit Pandey, G. S. S. Chalapathi, Dhruv Kumar   +7 more
doaj   +3 more sources

Denoising Vision Transformers

European Conference on Computer Vision
Accepted to ECCV2024. Project website: https://jiawei-yang.github.io/DenoisingViT/
Jiawei Yang 0002, Katie Z. Luo, Jiefeng Li, Congyue Deng, Leonidas J. Guibas, Dilip Krishnan, Kilian Q. Weinberger, Yonglong Tian, Yue Wang 0041   +8 more
openaire   +3 more sources

Rosette Trajectory MRI Reconstruction with Vision Transformers [PDF]

Tomography
Introduction: An efficient pipeline for rosette trajectory magnetic resonance imaging reconstruction is proposed, combining the inverse Fourier transform with a vision transformer (ViT) network enhanced with a convolutional layer.
Muhammed Fikret Yalcinbas, Cengizhan Ozturk, Onur Ozyurt, Uzay E. Emir, Ulas Bagci   +4 more
doaj   +2 more sources

Emerging Properties in Self-Supervised Vision Transformers [PDF]

IEEE International Conference on Computer Vision, 2021
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) [16] that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works
Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, J. Mairal, Piotr Bojanowski, Armand Joulin   +6 more
semanticscholar   +1 more source

A Survey on Vision Transformer [PDF]

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks.
Kai Han 0002, Yunhe Wang 0001, Hanting Chen, Xinghao Chen 0001, Jianyuan Guo, Zhenhua Liu 0003, Yehui Tang 0001, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang 0003, Yiman Zhang, Dacheng Tao   +12 more
openaire   +2 more sources

An Empirical Study of Training Self-Supervised Vision Transformers [PDF]

IEEE International Conference on Computer Vision, 2021
This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT).
Xinlei Chen, Saining Xie, Kaiming He
semanticscholar   +1 more source

Vision Transformers for Dense Prediction [PDF]

IEEE International Conference on Computer Vision, 2021
We introduce dense prediction transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks.
René Ranftl, Alexey Bochkovskiy, V. Koltun   +2 more
semanticscholar   +1 more source

CvT: Introducing Convolutions to Vision Transformers [PDF]

IEEE International Conference on Computer Vision, 2021
We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both de-signs.
Haiping Wu, Bin Xiao, N. Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang   +6 more
semanticscholar   +1 more source

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet [PDF]

IEEE International Conference on Computer Vision, 2021
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then
Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Francis E. H. Tay, Jiashi Feng, Shuicheng Yan   +7 more
semanticscholar   +1 more source