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

September 14, 2023

Interpretability-Aware Vision Transformer
Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Vision Transformer Inherent Interpretability Model Interpretability Self Interpretable Model

September 13, 2023

Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, Yannis Avrithis
Convolutional Neural Network Vision Transformer Attention Map Attention Based Pooling

September 12, 2023

Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks
Jindong Gu, Fangyun Wei, Philip Torr, Han Hu
Deep Neural Network Vision Transformer Native Robustness Black Box Attack ViT Lens Stochastic Defense Non Additive

September 11, 2023

September 10, 2023

DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices
Guanyu Xu, Zhiwei Hao, Yong Luo, Han Hu, Jianping An, Shiwen Mao
Vision Transformer Edge Device Collaborative Inference Vision Benchmark

September 8, 2023

Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts
Erik Daxberger, Floris Weers, Bowen Zhang, Tom Gunter, Ruoming Pang, Marcin Eichner, Michael Emmersberger, Yinfei Yang, Alexander Toshev, Xianzhi Du
Vision Transformer Sparse Mixture of Expert Sparse MoEs

September 7, 2023

September 6, 2023

September 4, 2023

September 2, 2023

Contrastive Feature Masking Open-Vocabulary Vision Transformer
Dahun Kim, Anelia Angelova, Weicheng Kuo
Vision Transformer Open Vocabulary Object Detection Zero Shot Transfer Contrastive Learning Objective Image Text Pretraining

September 1, 2023

Interpretable Medical Imagery Diagnosis with Self-Attentive Transformers: A Review of Explainable AI for Health Care
Tin Lai
Artificial Intelligence Vision Transformer Narrative Review Self Attention Explainable Artificial Intelligence xAI Community Health Management

Vision Transformer

Papers

Interpretability-Aware Vision Transformer

Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?

Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks

Mobile Vision Transformer-based Visual Object Tracking

Toward a Deeper Understanding: RetNet Viewed through Convolution

DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices

Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts

S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Combining pre-trained Vision Transformers and CIDER for Out Of Domain Detection

Improving diagnosis and prognosis of lung cancer using vision transformers: A scoping review

Compressing Vision Transformers for Low-Resource Visual Learning

Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images

A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking

Mask-Attention-Free Transformer for 3D Instance Segmentation

Locality-Aware Hyperspectral Classification

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

ExMobileViT: Lightweight Classifier Extension for Mobile Vision Transformer

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Interpretable Medical Imagery Diagnosis with Self-Attentive Transformers: A Review of Explainable AI for Health Care