AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

PyTorch code and checkpoints release for VanillaKD: https://arxiv.org/abs/2305.15781

Code for CVPR'24 Paper: Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens

Finetune MobileSAM with Less Than 4GB RAM!

VMamba: Visual State Space Models，code is based on mamba

LaTeX Thesis Template for the University of Chinese Academy of Sciences

Official PyTorch implementation of paper "Variation-aware Vision Transformer Quantization"

RS5M: a large-scale vision language dataset for remote sensing

[CVPR 2024 🔥] GeoChat, the first grounded Large Vision Language Model for Remote Sensing

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023

This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

(SaGe) Semantic-Aware Generation for Self-Supervised Visual Representation Learning

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

Prototype Mixture Models for Few-shot Semantic Segmentation

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

code for "Training Interpretable Convolutional NeuralNetworks by Differentiating Class-specific Filters"

More light-weight pytorch experiment management library!

Potato-CV is for programmer. It's brief and. emmm.... very potato. hahahha

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019)