Model Compression

CircConv: A Structured Convolution with Low Complexity AAAI 2019 Composite Binary Decomposition Networks AAAI 2019 Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition AAAI 2019 Compression of Acoustic Event Detection Models with Quantized Distillation Interspeech 2019 Compression of CTC-Trained Acoustic Models by Dynamic Frame-Wise Distillation or Segment-Wise N-Best Hypotheses Imitation Interspeech 2019 CondConv: Conditionally Parameterized Convolutions for Efficient Inference NeurIPS 2019 Cross Domain Model Compression by Structurally Weight Sharing CVPR 2019 Data-Distortion Guided Self-Distillation for Deep Neural Networks AAAI 2019 Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask NeurIPS 2019 Deep Neural Network Quantization via Layer-Wise Optimization Using Limited Training Data AAAI 2019 DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation NeurIPS 2019 Discrete Social Recommendation AAAI 2019 Double Quantization for Communication-Efficient Distributed Optimization NeurIPS 2019 ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model CVPR 2019 Efficient Multi-Domain Learning by Covariance Normalization CVPR 2019 Efficient Quantization for Neural Networks with Binary Weights and Low Bitwidth Activations AAAI 2019 Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition Interspeech 2019 Flambé: A Customizable Framework for Machine Learning Experiments ACL 2019 Fully Learnable Group Convolution for Acceleration of Deep Neural Networks CVPR 2019 Global Sparse Momentum SGD for Pruning Very Deep Neural Networks NeurIPS 2019 GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism NeurIPS 2019 Importance Estimation for Neural Network Pruning CVPR 2019 In-Place Zero-Space Memory Protection for CNN NeurIPS 2019 IRLAS: Inverse Reinforcement Learning for Architecture Search CVPR 2019 KAMA-NNs: Low-dimensional Rotation Based Neural Networks AISTATS 2019