1. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0. 5 mb model size;iandola;ArXiv Preprint,2016
2. MobileNets: Efficient convolutional neural networks for mobile vision applications;howard;CoRR,2017
3. Learning network size while training with ShrinkNets;leclerc;The Conference on Systems and Machine Learning,2018
4. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding;han;International Conference on Learning Representations,2016
5. Deep Feature Flow for Video Recognition