# Efficient-Computing

**Repository Path**: lxgyChen/Efficient-Computing

## Basic Information

- **Project Name**: Efficient-Computing
- **Description**: forked from https://github.com/huawei-noah/Efficient-Computing.git
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 2
- **Forks**: 0
- **Created**: 2023-09-22
- **Last Updated**: 2024-04-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Efficient Computing

This repo is a collection of Efficient-Computing methods developed by Huawei Noah's Ark Lab. 

- [Data-Efficient-Model-Compression](https://github.com/huawei-noah/Efficient-Computing/tree/master/Data-Efficient-Model-Compression) is a series of compression methods with no or little training data.
- [BinaryNetworks](https://github.com/huawei-noah/Efficient-Computing/tree/master/BinaryNetworks): Binary neural networks including [AdaBin (ECCV22)](https://arxiv.org/abs/2208.08084).
- [Distillation](https://github.com/huawei-noah/Efficient-Computing/tree/master/Distillation): Knowledge distillation methods including [ManifoldKD (NeurIPS22)](https://arxiv.org/pdf/2107.01378.pdf) and [VanillaKD (NeurIPS23)](https://arxiv.org/abs/2305.15781).
- [Pruning](https://github.com/huawei-noah/Efficient-Computing/tree/master/Pruning): Network pruning methods including [GAN-pruning (ICCV19)](https://arxiv.org/abs/1907.10804), [SCOP (NeurIPS20)](https://arxiv.org/abs/2010.10732) and [ManiDP (CVPR21)](https://openaccess.thecvf.com/content/CVPR2021/papers/Tang_Manifold_Regularized_Dynamic_Network_Pruning_CVPR_2021_paper.pdf).
- [Quantization](https://github.com/huawei-noah/Efficient-Computing/tree/master/Quantization): Model quantization methods including [DynamicQuant (CVPR22)](https://openaccess.thecvf.com/content/CVPR2022/html/Liu_Instance-Aware_Dynamic_Neural_Network_Quantization_CVPR_2022_paper.html).
- [Self-supervised](https://github.com/huawei-noah/Efficient-Computing/tree/master/Self-supervised): self-supervised learning including [FastMIM](https://arxiv.org/pdf/2212.06593.pdf) and [LocalMIM (CVPR23)](https://arxiv.org/abs/2303.05251).
- [TrainingAcceleration](https://github.com/huawei-noah/Efficient-Computing/tree/master/TrainingAcceleration): Accelerating neural network training via [NetworkExpansion (CVPR23)](https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Network_Expansion_for_Practical_Training_Acceleration_CVPR_2023_paper.pdf).
- [Detection](https://github.com/huawei-noah/Efficient-Computing/tree/master/Detection): Efficient object detectors including [Gold-YOLO (NeurIPS23)](https://arxiv.org/abs/2309.11331).