Home

Awesome

Efficient AI Backbones

including GhostNet, TNT (Transformer in Transformer), AugViT, WaveMLP and ViG developed by Huawei Noah's Ark Lab.

News

2024/02/27 The paper of ParameterNet is accepted by CVPR 2024.

2022/12/01 The code of NeurIPS 2022 (Spotlight) GhostNetV2 is released at ./ghostnetv2_pytorch.

2022/11/13 The code of IJCV 2022 G-Ghost RegNet is released at ./g_ghost_pytorch.

2022/06/17 The code of NeurIPS 2022 Vision GNN (ViG) is released at ./vig_pytorch.

2022/02/06 Transformer in Transformer (TNT) is selected as the Most Influential NeurIPS 2021 Papers.

2021/09/18 The extended version of Versatile Filters is accepted by T-PAMI.

2021/08/30 GhostNet paper is selected as the Most Influential CVPR 2020 Papers.

Model zoo

ModelPaperPytorch codeMindSpore code
GhostNetGhostNet: More Features from Cheap Operations. [CVPR 2020]./ghostnet_pytorchMindSpore Model Zoo
GhostNetV2GhostNetV2: Enhance Cheap Operation with Long-Range Attention. [NeurIPS 2022 Spotlight]./ghostnetv2_pytorchMindSpore Model Zoo
G-GhostNetGhostNets on Heterogeneous Devices via Cheap Operations. [IJCV 2022]./g_ghost_pytorchMindSpore Model Zoo
TinyNetModel Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets. [NeurIPS 2020]./tinynet_pytorchMindSpore Model Zoo
TNTTransformer in Transformer. [NeurIPS 2021]./tnt_pytorchMindSpore Model Zoo
PyramidTNTPyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture. [CVPR 2022 Workshop]./tnt_pytorchMindSpore Model Zoo
CMTCMT: Convolutional Neural Networks Meet Vision Transformers. [CVPR 2022]./cmt_pytorchMindSpore Model Zoo
AugViTAugmented Shortcuts for Vision Transformers. [NeurIPS 2021]./augvit_pytorchMindSpore Model Zoo
SNN-MLPBrain-inspired Multilayer Perceptron with Spiking Neurons. [CVPR 2022]./snnmlp_pytorchMindSpore Model Zoo
WaveMLPAn Image Patch is a Wave: Quantum Inspired Vision MLP. [CVPR 2022]./wavemlp_pytorchMindSpore Model Zoo
ViGVision GNN: An Image is Worth Graph of Nodes. [NeurIPS 2022]./vig_pytorch-
LegoNetLegoNet: Efficient Convolutional Neural Networks with Lego Filters. [ICML 2019]./legonet_pytorch-
Versatile FiltersLearning Versatile Filters for Efficient Convolutional Neural Networks. [NeurIPS 2018]./versatile_filters-
ParameterNetParameterNet: Parameters Are All You Need. [CVPR 2024]../parameternet_pytorch-