Efficient-AI-Backbones
EfficientFormer
Efficient-AI-Backbones | EfficientFormer | |
---|---|---|
3 | 2 | |
3,816 | 944 | |
1.5% | 0.7% | |
5.8 | 3.3 | |
7 days ago | 9 months ago | |
Python | Python | |
- | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Efficient-AI-Backbones
-
Researchers From China Introduce Vision GNN (ViG): A Graph Neural Network For Computer Vision Systems
Continue reading | Check out the paper, github
- GNN for computer vision, beating CNN & Transformer
-
GNN can also work well on computer vision
Vision GNN: An Image is Worth Graph of Nodes Network architecture plays a key role in the deep learning-based computer vision system. The widely-used convolutional neural network and transformer treat the image as a grid or sequence structure, which is not flexible to capture irregular and complex objects. In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. We first split the image to a number of patches which are viewed as nodes, and construct a graph by connecting the nearest neighbors. Based on the graph representation of images, we build our ViG model to transform and exchange information among all the nodes. ViG consists of two basic modules: Grapher module with graph convolution for aggregating and updating graph information, and FFN module with two linear layers for node feature transformation. Both isotropic and pyramid architectures of ViG are built with different model sizes. Extensive experiments on image recognition and object detection tasks demonstrate the superiority of our ViG architecture. We hope this pioneering study of GNN on general visual tasks will provide useful inspiration and experience for future research. The PyTroch code will be available at https://github.com/huawei-noah/CV-Backbones.
EfficientFormer
-
A look at Apple’s new Transformer-powered predictive text model
I'm pretty fatigued on constantly providing references and sources in this thread but an example of what they've made availably publicly:
https://github.com/snap-research/EfficientFormer
-
Snap and Northeastern University Researchers Propose EfficientFormer: A Vision Transformer That Runs As Fast As MobileNet While Maintaining High Performance
Continue reading | Check out the paper, github
What are some alternatives?
MPViT - [CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction
PyTorch-Model-Compare - Compare neural networks by their feature similarity
FQ-ViT - [IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
dytox - Dynamic Token Expansion with Continual Transformers, accepted at CVPR 2022
transfiner - Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022
predictive-spy - Spying on Apple’s new predictive text model
RethinkVSRAlignment - (NIPS 2022) Rethinking Alignment in Video Super-Resolution Transformers
llama.cpp - LLM inference in C/C++
deepvision - PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, NeRF, SegFormer, MixTransformer, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, etc.
ml-cvnets - CVNets: A library for training computer vision networks
PyTorch-Vision-Transformer-ViT-MNIST-CIFAR10 - Simplified Pytorch implementation of Vision Transformer (ViT) for small datasets like MNIST, FashionMNIST, SVHN and CIFAR10.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.