model compression

Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation EMNLP 2020 Low-Rank Compression of Neural Nets: Learning the Rank of Each Layer CVPR 2020 Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020 MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition Interspeech 2020 MemNAS: Memory-Efficient Neural Architecture Search With Grow-Trim Learning CVPR 2020 Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP EMNLP 2020 MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers NeurIPS 2020 Mixed Precision DNNs: All you need is a good parametrization ICLR 2020 MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices CVPR 2020 MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices ACL 2020 MoBiNet: A Mobile Binary Network for Image Classification WACV 2020 Model Fusion via Optimal Transport NeurIPS 2020 Modularized Transfomer-based Ranking Framework EMNLP 2020 Multiclass Neural Network Minimization via Tropical Newton Polytope Approximation ICML 2020 Multi-Dimensional Pruning: A Unified Framework for Model Compression CVPR 2020 MUXConv: Information Multiplexing in Convolutional Neural Networks CVPR 2020 Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio CVPR 2020 Neural Architecture Search for Keyword Spotting Interspeech 2020 Neural Architecture Search for Lightweight Non-Local Networks CVPR 2020 Neural Inheritance Relation Guided One-Shot Layer Assignment Search AAAI 2020 Neural Network Pruning With Residual-Connections and Limited-Data CVPR 2020 NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks CVPR 2020 Neuron-level Structured Pruning using Polarization Regularizer NeurIPS 2020 Neuron Merging: Compensating for Pruned Neurons NeurIPS 2020 Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free NeurIPS 2020