Vision Transformer

Vision Transformers (ViTs) adapt the transformer architecture, initially designed for natural language processing, to image analysis by treating images as sequences of patches. Current research focuses on improving ViT efficiency and robustness through techniques like token pruning, attention engineering, and hybrid models combining ViTs with convolutional neural networks or other architectures (e.g., Mamba). These advancements are driving progress in various applications, including medical image analysis, object detection, and spatiotemporal prediction, by offering improved accuracy and efficiency compared to traditional convolutional neural networks in specific tasks.

Papers

June 8, 2023

Is Attentional Channel Processing Design Required? Comprehensive Analysis Of Robustness Between Vision Transformers And Fully Attentional Networks
Abhishri Ajit Medewar, Swanand Ashokrao Kavitkar
Vision Transformer Native Robustness Channel Attention Attention Network Comprehensive Analysis Traditional CNNs
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Seungryong Yoo, Eunji Kim, Dahuin Jung, Jungbeom Lee, Sungroh Yoon
Vision Transformer Self Supervised Vision Transformer Image Classification Task Visual Prompt Tuning Pre Trained ViT
Multi-Scale And Token Mergence: Make Your ViT More Efficient
Zhe Bian, Zhe Wang, Wenqiang Han, Kangping Wang
Vision Transformer Multi Head Self Attention Token Pruning Token Merging

June 7, 2023

Revising deep learning methods in parking lot occupancy detection
Anastasia Martynova, Mikhail Kuznetsov, Vadim Porvatov, Vladislav Tishin, Andrey Kuznetsov, Natalia Semenova, Ksenia Kuznetsova
Deep Learning Vision Transformer Smart City EfficientNet Algorithm
Efficient Vision Transformer for Human Pose Estimation via Patch Selection
Kaleab A. Kinfu, Rene Vidal
Convolutional Neural Network Vision Transformer High Resolution Image Human Pose Estimation 2 Dimensional Human Pose Estimation Efficient Vision Transformer Patch Selection
TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation
Rui Sun, Tao Lei, Weichuan Zhang, Yong Wan, Yong Xia, Asoke K. Nandi
Convolutional Neural Network Vision Transformer Medical Image Segmentation Convolution Operation

June 6, 2023

Human-imperceptible, Machine-recognizable Images
Fusheng Hao, Fengxiang He, Yikai Wang, Fuxiang Wu, Jing Zhang, Jun Cheng, Dacheng Tao
Vision Transformer Supervised ImageNet Privacy Preserving Learning
CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation
Tao Lei, Rui Sun, Xuan Wang, Yingbo Wang, Xi He, Asoke Nandi
Convolutional Neural Network Vision Transformer Medical Image Segmentation Deformable Convolution Human Hand

June 3, 2023

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers
Chenyang Lu, Daan de Geus, Gijs Dubbelman
Vision Transformer Semantic Segmentation Semantic Segmentation Network Segmentation Quality Efficient Semantic Segmentation Token Optimization Segmentation Decoder
Memorization Capacity of Multi-Head Attention in Transformers
Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis
Vision Transformer Transformer Megatron Decepticons Human Attention Attention Layer Multi Head Attention Mechanism Memorization Capacity Memorization Capability

June 1, 2023

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer
Vision Transformer Video Recognition Hierarchical Vision Transformer Pretext Task Bell and Whistle
Lightweight Vision Transformer with Bidirectional Interaction
Qihang Fan, Huaibo Huang, Xiaoqiang Zhou, Ran He
Vision Transformer Fine Grained Self Attention Vision Backbone

May 31, 2023

Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects
Stefan Thalhammer, Jean-Baptiste Weibel, Markus Vincze, Jose Garcia-Rodriguez
Vision Transformer Pre Trained Vision Transformer Self Supervised Vision Transformer Deep Template Pose Estimator Novel Object Template Matching
CVSNet: A Computer Implementation for Central Visual System of The Brain
Ruimin Gao, Hao Zou, Zhekai Duan
Deep Learning Vision Transformer Computer Vision Object Recognition Brain Function Human Visual System Implementation Detail

May 30, 2023

Vision Transformer

Papers

Is Attentional Channel Processing Design Required? Comprehensive Analysis Of Robustness Between Vision Transformers And Fully Attentional Networks

Improving Visual Prompt Tuning for Self-supervised Vision Transformers

Multi-Scale And Token Mergence: Make Your ViT More Efficient

Revising deep learning methods in parking lot occupancy detection

Efficient Vision Transformer for Human Pose Estimation via Patch Selection

TEC-Net: Vision Transformer Embrace Convolutional Neural Networks for Medical Image Segmentation

Human-imperceptible, Machine-recognizable Images

CiT-Net: Convolutional Neural Networks Hand in Hand with Vision Transformers for Medical Image Segmentation

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers

Memorization Capacity of Multi-Head Attention in Transformers

Centered Self-Attention Layers

A Novel Vision Transformer with Residual in Self-attention for Biomedical Image Classification

nnMobileNet: Rethinking CNN for Retinopathy Research

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

Lightweight Vision Transformer with Bidirectional Interaction

Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects

CVSNet: A Computer Implementation for Central Visual System of The Brain

Vision Transformers for Mobile Applications: A Short Survey

Prompt-Based Tuning of Transformer Models for Multi-Center Medical Image Segmentation of Head and Neck Cancer

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts