Model Compression

Mixed-Privacy Forgetting in Deep Networks CVPR 2021 MobileDets: Searching for Object Detection Architectures for Mobile Accelerators CVPR 2021 MoViNets: Mobile Video Networks for Efficient Video Recognition CVPR 2021 Multi-split Reversible Transformers Can Enhance Neural Machine Translation EACL 2021 NetAdaptV2: Efficient Neural Architecture Search With Fast Super-Network Training and Architecture Optimization CVPR 2021 Network Pruning That Matters: A Case Study on Retraining Variants ICLR 2021 Network Pruning via Performance Maximization CVPR 2021 Network Quantization With Element-Wise Gradient Scaling CVPR 2021 Neural gradients are near-lognormal: improved quantized and sparse training ICLR 2021 NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021 On-Device Streaming Transformer-Based End-to-End Speech Recognition Interspeech 2021 Only Train Once: A One-Shot Neural Network Training And Pruning Framework NeurIPS 2021 On the Predictability of Pruning Across Scales ICML 2021 OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization AAAI 2021 Optimal Quantization Using Scaled Codebook CVPR 2021 Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization AAAI 2021 Optimizing Reusable Knowledge for Continual Learning via Metalearning NeurIPS 2021 Parameter-Efficient Transfer Learning with Diff Pruning ACL 2021 PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition NeurIPS 2021 Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021 Post-Hoc Uncertainty Calibration for Domain Drift Scenarios CVPR 2021 Post-Training Sparsity-Aware Quantization NeurIPS 2021 PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation Interspeech 2021 Practical Single-Image Super-Resolution Using Look-Up Table CVPR 2021 Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services CVPR 2021