Model Compression

CondenseNet: An Efficient DenseNet Using Learned Group Convolutions CVPR 2018 Constructing Fast Network through Deconstruction of Convolution NeurIPS 2018 Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions ICML 2018 Deterministic Binary Filters for Convolutional Neural Networks IJCAI 2018 Dropout as a Low-Rank Regularizer for Matrix Factorization AISTATS 2018 Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling EMNLP 2018 Efficient Parametrization of Multi-Domain Deep Neural Networks CVPR 2018 Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks CVPR 2018 FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network NeurIPS 2018 Feature Quantization for Defending Against Distortion of Images CVPR 2018 Frequency-Domain Dynamic Pruning for Convolutional Neural Networks NeurIPS 2018 GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training NeurIPS 2018 GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking NeurIPS 2018 Heterogeneous Bitwidth Binarization in Convolutional Neural Networks NeurIPS 2018 HitNet: Hybrid Ternary Recurrent Neural Network NeurIPS 2018 HydraNets: Specialized Dynamic Architectures for Efficient Inference CVPR 2018 Hypernetwork-based Implicit Posterior Estimation and Model Averaging of CNN ACML 2018 Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models Interspeech 2018 Interleaved Structured Sparse Convolutional Neural Networks CVPR 2018 Knowledge Distillation by On-the-Fly Native Ensemble NeurIPS 2018 Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition CVPR 2018 Learning Compressed Transforms with Low Displacement Rank NeurIPS 2018 “Learning-Compression” Algorithms for Neural Net Pruning CVPR 2018 Learning Versatile Filters for Efficient Convolutional Neural Networks NeurIPS 2018 Low-rank passthrough neural networks ACL 2018