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

May 29, 2023

Solar Irradiance Anticipative Transformer
Thomas M. Mercier, Tasmiat Rahman, Amin Sabet
Vision Transformer Sky Image Datasets Anticipative Transformer

May 27, 2023

May 26, 2023

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
Jinqi Xiao, Miao Yin, Yu Gong, Xiao Zang, Jian Ren, Bo Yuan
Neural Network Vision Transformer Compression Technique Prompt Customization Vision Transformer Compression

May 24, 2023

May 23, 2023

Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers
Giulia Rizzoli, Donald Shenaj, Pietro Zanuttigh
Vision Transformer Semantic Segmentation Source Free Domain Adaptation Source Free Depth Aware

May 22, 2023

May 21, 2023

Bi-ViT: Pushing the Limit of Vision Transformer Quantization
Yanjing Li, Sheng Xu, Mingbao Lin, Xianbin Cao, Chuanjian Liu, Xiao Sun, Baochang Zhang
Vision Transformer Supervised ImageNet Continuum Limit ViT Lens Large Pre Trained Vision Transformer Quantization Binary Vision Transformer

May 18, 2023

May 17, 2023

May 16, 2023

Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Jinsong Shi, Pan Gao, Aljosa Smolic
Vision Transformer Transformer Based Image Quality Assessment Perceptual Quality Reference Image Quality Assessment Blind Image Quality Assessment

Vision Transformer

Papers

Solar Irradiance Anticipative Transformer

Scalable Transformer for PDE Surrogate Modeling

Vision Transformers for Small Histological Datasets Learned through Knowledge Distillation

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models

Image Classification of Stroke Blood Clot Origin using Deep Convolutional Neural Networks and Visual Transformers

Making Vision Transformers Truly Shift-Equivariant

Imitating Task and Motion Planning with Visuomotor Transformers

BinaryViT: Towards Efficient and Accurate Binary Vision Transformers

Quantifying Character Similarity with Vision Transformers

Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers

Efficient Large-Scale Visual Representation Learning And Evaluation

U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

VanillaNet: the Power of Minimalism in Deep Learning

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses

Boost Vision Transformer with GPU-Friendly Sparsity and Quantization

Transfer Learning for Fine-grained Classification Using Semi-supervised Learning and Visual Transformers

A survey of the Vision Transformers and its CNN-Transformer based Variants

Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token