iyeee

NCO-solvers-for-VRP

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

open-aff

code and trained models for "Attentional Feature Fusion"

mvit

Code Release for MViTv2 on Image Recognition.

mlp-mixer-pytorch

An All-MLP solution for Vision, from Google AI

TransReID

[ICCV-2021] TransReID: Transformer-based Object Re-Identification

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

DCNv2

Deformable Convolutional Networks v2 with Pytorch

NonDeepNetworks

Official Code for "Non-deep Networks"

SimAM

The official pytorch implemention of our ICML-2021 paper "SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks".

ECANet

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

SUES-200-Benchmark

SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite

mobilevit-pytorch

A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"

EfficientFormer

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

Cream

This is a collection of our NAS and Vision Transformer work.

SwiftFormer

[ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

pytorch-mobilenet-v3

MobileNetV3 in pytorch and ImageNet pretrained models

MobileNeXt

MobileViTv3

cls_KD

'NKD and USKD' (ICCV 2023) and 'ViTKD' (CVPRW 2024)

Sample4Geo

texture-vs-shape

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Switchable-Whitening

Code for Switchable Whitening (ICCV2019)

IBN-Net

Instance-Batch Normalization Networks (ECCV2018)

CFPNet

Centralized Feature Pyramid for Object Detection

vision_transformer

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

maxim

[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.

Awesome-Vision-Attentions

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

netron

Visualizer for neural network, deep learning and machine learning models