model compression

Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization AAAI 2021 Overfitting the Data: Compact Neural Video Delivery via Content-Aware Feature Modulation ICCV 2021 Parameter-Efficient Transfer Learning with Diff Pruning ACL 2021 Peer Collaborative Learning for Online Knowledge Distillation AAAI 2021 Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021 Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021 Positive-Congruent Training: Towards Regression-Free Model Updates CVPR 2021 Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision AAAI 2021 Post-Training Sparsity-Aware Quantization NeurIPS 2021 Powerpropagation: A sparsity inducing weight reparameterisation NeurIPS 2021 PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation Interspeech 2021 Preserved central model for faster bidirectional compression in distributed settings NeurIPS 2021 ProFormer: Towards On-Device LSH Projection Based Transformers EACL 2021 Progressive Network Grafting for Few-Shot Knowledge Distillation AAAI 2021 Pruning Neural Machine Translation for Speed Using Group Lasso EMNLP 2021 Pruning Neural Networks at Initialization: Why Are We Missing the Mark? ICLR 2021 Pruning of Deep Spiking Neural Networks through Gradient Rewiring IJCAI 2021 QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks CVPR 2021 Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes NeurIPS 2021 QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning NeurIPS 2021 RankDistil: Knowledge Distillation for Ranking AISTATS 2021 RaScaNet: Learning Tiny Models by Raster-Scanning Images CVPR 2021 ReadOnce Transformers: Reusable Representations of Text for Transformers ACL 2021 ReDet: A Rotation-Equivariant Detector for Aerial Object Detection CVPR 2021 RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks NeurIPS 2021