Open-source alternatives to ViTAE

This repo contains the official PyTorch code and pre-trained models for the Dynamic Vision Transformer (DVT).

GLiT: Neural Architecture Search for Global and Local Image Transformer Code for GLiT: Neural Architecture Search for Global and Local Image Transformer accepted by ICCV2021

This is a PyTorch implementation of CoAtNet specified in "CoAtNet: Marrying Convolution and Attention for All Data Sizes", arXiv 2021.

This is a PyTorch implementation of MobileViT specified in "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer", arXiv 2021.

ECCV 2022Code for paper "DaViT: Dual Attention Vision Transformer"

This repository contains PyTorch code for ConViT. It builds on code from the Data-Efficient Vision Transformer and from timm.

This repo contains the PyTorch version of 8 model definitions (Atto, Femto, Pico, Nano, Tiny, Base, Large, Huge), pre-training/fine-tuning code and pre-trained weights (converted from JAX weights trained on TPU) for our ConvNeXt V2 paper.

DeiT is a PyTorch vision transformer framework designed for image classification. It implements a transformer-based architecture that processes images as sequences of flattened patches using self-attention layers and position-aware sequence modeling instead of convolutional filters. The project focuses on data-efficient training through a knowledge distillation framework. This system allows a student model to mimic the soft labels of a high-performance teacher model to improve accuracy and generalization, particularly when training on smaller datasets. The library covers the full development

DiT is a latent diffusion model and transformer-based generative AI framework implemented in PyTorch. It functions as a class-conditional image generator that replaces traditional convolutional backbones with a transformer architecture to synthesize high-fidelity images. The project utilizes patch-based latent processing and latent space compression to operate on low-dimensional image representations. It incorporates class-conditional guidance and adjustable guidance scales to control the visual content of generated images during the sampling process. The framework covers distributed model t

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

CV-Backbones is a computer vision backbone library and model zoo providing a collection of pre-defined neural network architectures for extracting visual features and processing image data. It serves as a PyTorch vision framework of reusable deep learning components designed for image analysis and visual representation learning. The library focuses on efficient neural network architectures to reduce computational overhead while maintaining feature extraction performance. This is achieved through the implementation of lightweight model designs such as GhostNet and MLP. The project covers a br

The official implementation of the paper "Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition". Our code is based on timm and ConvNeXt.