XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks [ECCV 2016] [code]
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients [arXive 2016] [code]
Sparsifying Neural Network Connections for Face Recognition [arXive 2015]
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding [ICLR 2016] [code]
Learning Structured Sparsity in Deep Neural Networks [NIPS 2016] [code]
Group Sparse Regularization for Deep Neural Networks [arXive 2016]
Deep Networks with Stochastic Depth [arXive 2016] [code]
BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks [ICPR 2016] [code]
Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution [arXive 2017]
Spatially Adaptive Computation Time for Residual Networks [arXice 2016]
Distilling the Knowledge in a Neural Network [arXive 2015]
FITNETS: HINTS FOR THIN DEEP NETS [ICLR 2015] [code]
Do Deep Nets Really Need to be Deep? [NIPS 2014]
Deep Model Compression: Distilling Knowledge from Noisy Teachers [arXive 2016]