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

August 20, 2023

August 19, 2023

Towards a High-Performance Object Detector: Insights from Drone Detection Using ViT and CNN-based Deep Learning Models
Junyang Zhang
Vision Transformer Deep Learning Model DCU Insight AQ Drone Detection UAV Dataset

August 18, 2023

August 17, 2023

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning
Guangyu Sun, Matias Mendieta, Jun Luo, Shandong Wu, Chen Chen
Vision Transformer Personalized Federated Learning Decentralized Learning Self Attention Layer Model Personalization

August 16, 2023

SkinDistilViT: Lightweight Vision Transformer for Skin Lesion Classification
Vlad-Constantin Lungu-Stan, Dumitru-Clementin Cercel, Florin Pop
Vision Transformer Knowledge Distillation Skin Lesion Skin Cancer Balanced Classification Melanoma Diagnosis

August 15, 2023

SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays Classification
Raza Imam, Ibrahim Almakky, Salma Alrashdi, Baketah Alrashdi, Mohammad Yaqub
Vision Transformer Adversarial Example Adversarial Training Adversarial Perturbation Chest X Ray Adversarial Distillation Defensive Distillation

August 14, 2023

August 12, 2023

Revisiting Vision Transformer from the View of Path Ensemble
Shuning Chang, Pichao Wang, Hao Luo, Fan Wang, Mike Zheng Shou
Vision Transformer Multi Head Self Attention Best View High Quality Representation Path Modeling Ensemble Neural Network

August 11, 2023

Experts Weights Averaging: A New General Training Scheme for Vision Transformers
Yongqi Huang, Peng Ye, Xiaoshui Huang, Sheng Li, Tao Chen, Tong He, Wanli Ouyang
Convolutional Neural Network Vision Transformer Structural Re Parameterization Training Scheme

August 10, 2023

Vision Backbone Enhancement via Multi-Stage Cross-Scale Attention
Liang Shang, Yanli Liu, Zhengyang Lou, Shuxue Quan, Nagesh Adluru, Bochen Guan, William A. Sethares
Convolutional Neural Network Vision Transformer Attention Module Feature Map Vision Backbone Cross Scale Attention