Skip to content

Latest commit

 

History

History
31 lines (19 loc) · 2.87 KB

NetworkCompression.md

File metadata and controls

31 lines (19 loc) · 2.87 KB
Raw

Network Compression

Group Conv

    • Forrest N. Iandola, Song Han, et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size." (2017). [pdf] (SqueezeNet)
    • Howard, Andrew G, et al. "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications." (2017). [pdf] (MobileNets)
    • Zhang, Xiangyu, et al. "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices." (2017). [pdf] (ShuffleNet)
    • Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Quoc V. Le "Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation." (2018). [pdf] (MobileNetV2)
    • Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen et al. "IMnasNet: Platform-Aware Neural Architecture Search for Mobile." (2018). [pdf] (IMnasNet)

Distilling

    • Geoffrey Hinton, Oriol Vinyals, Jeff Dean. "Distilling the Knowledge in a Neural Network." CVPR(2014). [pdf] (Distilling)
    • Romero, Adriana, et al. "FitNets: Hints for Thin Deep Nets.." Computer Science (2014). [pdf] (FitNets)
    • Sergey Zagoruyko, Nikos Komodakis "Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer." (2016). [pdf] [github](attention-transfer)
    • Zhou, Guorui, et al. "Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net." (2017). [pdf] (Launching)
    • Junho Yim, Donggyu Joo,Jihoon Bae, Junmo Kim et al. "A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning." CVPR(2017). [pdf]
    • Q Li, S Jin, J Yan et al. "Mimicking Very Efficient Network for Object Detection." CVPR(2017). [pdf] (Mimicking)

Pruning

    • Gao Huang et al. "CondenseNet: An Efficient DenseNet using Learned Group Convolutions." (2017). [pdf] [github](CondenseNet)

Review

    • Yu Cheng, Duo Wang, et al. "A Survey of Model Compression and Acceleration for Deep Neural Networks." IEEE Signal Processing Magazine(2017). [pdf]