Model Compression

Model Fusion via Optimal Transport NeurIPS 2020 Movement Pruning: Adaptive Sparsity by Fine-Tuning NeurIPS 2020 Multi-Dimensional Pruning: A Unified Framework for Model Compression CVPR 2020 Neural Epitome Search for Architecture-Agnostic Network Compression ICLR 2020 Neural Network Pruning With Residual-Connections and Limited-Data CVPR 2020 Neuron Merging: Compensating for Pruned Neurons NeurIPS 2020 Once-for-All: Train One Network and Specialize it for Efficient Deployment ICLR 2020 One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation ICLR 2020 On the Sparsity of Neural Machine Translation Models EMNLP 2020 Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient NeurIPS 2020 Passport-aware Normalization for Deep Model Protection NeurIPS 2020 PENNI: Pruned Kernel Sharing for Efficient CNN Inference ICML 2020 Picking Winning Tickets Before Training by Preserving Gradient Flow ICLR 2020 P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection IJCAI 2020 Playing Atari with Six Neurons (Extended Abstract) IJCAI 2020 Position-based Scaled Gradient for Model Quantization and Pruning NeurIPS 2020 Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks ICLR 2020 Protecting Geolocation Privacy of Photo Collections AAAI 2020 Pruning Filter in Filter NeurIPS 2020 Pruning neural networks without any data by iteratively conserving synaptic flow NeurIPS 2020 Rank and run-time aware compression of NLP Applications EMNLP 2020 Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning AAAI 2020 Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts NeurIPS 2020 Revisiting Knowledge Distillation via Label Smoothing Regularization CVPR 2020 Robust Quantization: One Model to Rule Them All NeurIPS 2020