Popular GitHub Repositories for Vision Transformers

Recent Transformer-based CV and related works.

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".

??? HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

Implementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorch

Implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

Library - Vanilla, ViT, DeiT, BERT, GPT

Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]

Recent Advances on Efficient Vision Transformers

This repository hosts code for converting the original Vision Transformer models (JAX) to TensorFlow.

This repository shows various ways of deploying a vision model (TensorFlow) from ? Transformers.

Implementation of VisionLLaMA from the paper: "VisionLLaMA: A Unified LLaMA Interface for Vision Tasks" in PyTorch and Zeta

Feature Selection Gates with Gradient Routing

Code for the paper Cross Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection

ViT Inference server from timm library

? Workshop in AI Deployment (INF-1600, UiT)