residual-attention-network

Attention Network

An implementation of a deep neural network architecture using attention mechanisms and residual connections for image classification tasks.

Residual Attention Network for Image Classification

GitHub

554 stars
24 watching
214 forks
last commit: about 9 years ago
Linked from 1 awesome list

attentioncvpr-2017image-classification

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
koichiro11/residual-attention-networkAn image classification neural network implementation using attention mechanisms and residual learning94
pistony/residualattentionnetworkA Gluon implementation of Residual Attention Network for image classification tasks108
tengshaofeng/residualattentionnetwork-pytorchImplementing a deep learning framework for image classification using Residual Attention Network architecture682
bruinxiong/modified-crunet-and-residual-attention-network.mxnetAn MXNet implementation of a modified deep neural network architecture for image classification67
focalnet/networks-beyond-attentionA collection of modern neural network architectures for computer vision tasks that don't use self-attention mechanisms.77
hszhao/psanetA deep learning framework for semantic segmentation with spatial attention mechanisms218
fyu/drnAn open-source implementation of dilated residual networks for image classification and segmentation tasks.1,104
songhan/squeezenet-residualAn optimized neural network architecture for image classification tasks by combining SqueezeNet with residual connections.155
tqtg/hierarchical-attention-networksAn implementation of a neural network architecture for document classification using hierarchical attention mechanisms87
kaiminghe/resnet-1k-layersRepresents a neural network architecture with 1K layers, designed for image recognition tasks.909
ozan-oktay/attention-gated-networksAn implementation of attention gates in convolutional neural networks for image classification and segmentation tasks1,927
zhouyanzhao/ornA deep learning framework implementation of an oriented response network for visual recognition tasks223
cszn/srmdDevelops a single convolutional network to handle various image degradations with improved scalability and efficiency427
szagoruyko/wide-residual-networksAn experimental study on residual networks to improve depth and width trade-offs in neural networks1,299
forresti/squeezenetProvides pre-trained models and training configurations for a deep neural network architecture optimized for image classification tasks2,181