← Keywords

vision transformer

1091 papers

Explore in graph

Also known as

VITE VIT CLIP-VIT VT

Co-occurring keywords

image classification (1943) semantic segmentation (3179) model compression (3283) self-supervised learning (3751) attention mechanism (3975) convolutional neural network (4216) object detection (2759) transfer learning (5442) representation learning (6174) knowledge distillation (3680)

Papers

CoAtNet: Marrying Convolution and Attention for All Data Sizes NIPS 2021
Blending Anti-Aliasing into Vision Transformer NIPS 2021
Dynamic Grained Encoder for Vision Transformers NIPS 2021
HRFormer: High-Resolution Vision Transformer for Dense Predict NIPS 2021
Scaling Vision with Sparse Mixture of Experts NIPS 2021
CvT: Introducing Convolutions to Vision Transformers ICCV 2021
GLiT: Neural Architecture Search for Global and Local Image Transformer ICCV 2021
Searching the Search Space of Vision Transformer NIPS 2021
TransReID: Transformer-Based Object Re-Identification ICCV 2021
LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference ICCV 2021
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding ICCV 2021
Pay Attention to MLPs NIPS 2021
Twins: Revisiting the Design of Spatial Attention in Vision Transformers NIPS 2021
Shifted Chunk Transformer for Spatio-Temporal Representational Learning NIPS 2021
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition NIPS 2021
Glance-and-Gaze Vision Transformer NIPS 2021
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification NIPS 2021
Augmented Shortcuts for Vision Transformers NIPS 2021
ResT: An Efficient Transformer for Visual Recognition NIPS 2021
All Tokens Matter: Token Labeling for Training Better Vision Transformers NIPS 2021
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model NIPS 2021
MST: Masked Self-Supervised Transformer for Visual Representation NIPS 2021
Rethinking and Improving Relative Position Encoding for Vision Transformer ICCV 2021
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions ICCV 2021
Partial success in closing the gap between human and machine vision NIPS 2021