ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation [2018 arXiv]
Slimmable Neural Networks [2019 ICLR] [code: pytorch]
PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural Networks [2018 NIPS] [code: tensorflow]
MnasNet: Platform-Aware Neural Architecture Search for Mobile [2018 arXiv] [code: mxnet pytorch]
Progressive Neural Architecture Search [2018 ECCV] [code: tensorflow tensorflow pytorch]
Learning Transferable Architectures for Scalable Image Recognition [2017 arXiv] [code: tensorflow]
Interleaved Group Convolutions for Deep Neural Networks [2018 BMVC] [code: mxnet]
IGCV2: Interleaved Structured Sparse Convolutional Neural Networks [2018 CVPR]
Interleaved Group Convolutions for Deep Neural Networks [2017 ICCV] [code: mxnet]
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design [2018 ECCV] [code: caffe]
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices [2018 CVPR] [code: caffe]
MobileNetV2: Inverted Residuals and Linear Bottlenecks [2018 CVPR] [code: tensorflow caffe]
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [2017 arXiv] [code: tensorflow caffe]
SqueezeNext: Hardware-Aware Neural Network Design [2018 CVPR] [code: caffe tensorflow]
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size [2016 arXiv] [code: caffe]
Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications [2018 IJCNN] [code: pytorch]
FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy [2018 arXiv]
Pelee: A Real-Time Object Detection System on Mobile Devices [2018 NIPS] [code: caffe]