Model Compression

Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021 Post-Training Sparsity-Aware Quantization NeurIPS 2021 Prefix-Tuning: Optimizing Continuous Prompts for Generation ACL 2021 ProFlip: Targeted Trojan Attack With Progressive Bit Flips ICCV 2021 Progressive Skeletonization: Trimming more fat from a network at initialization ICLR 2021 Protecting DNNs from Theft using an Ensemble of Diverse Models ICLR 2021 Pruning of Deep Spiking Neural Networks through Gradient Rewiring IJCAI 2021 Pruning Randomly Initialized Neural Networks with Iterative Randomization NeurIPS 2021 Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples NeurIPS 2021 QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks CVPR 2021 Random Noise Defense Against Query-Based Black-Box Attacks NeurIPS 2021 Rapid Speaker Adaptation for Conformer Transducer: Attention and Bias Are All You Need Interspeech 2021 RDI-Net: Relational Dynamic Inference Networks ICCV 2021 Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks ICLR 2021 ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting ICCV 2021 Rethinking Network Pruning – under the Pre-train and Fine-tune Paradigm NAACL 2021 Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better ICCV 2021 Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme NeurIPS 2021 Revisiting Knowledge Distillation: An Inheritance and Exploration Framework CVPR 2021 Revisiting Pretraining with Adapters ACL 2021 Robust Pruning at Initialization ICLR 2021 Robust Transfer Learning with Pretrained Language Models through Adapters ACL 2021 RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation EMNLP 2021 S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NeurIPS 2021 SAFENet: A Secure, Accurate and Fast Neural Network Inference ICLR 2021