Model Compression

Learning Student-Friendly Teacher Networks for Knowledge Distillation NeurIPS 2021 Learning to Augment for Data-scarce Domain BERT Knowledge Distillation AAAI 2021 Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension EMNLP 2021 Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021 LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search CVPR 2021 Lipschitz Continuity Guided Knowledge Distillation ICCV 2021 Manifold Regularized Dynamic Network Pruning CVPR 2021 Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ACL 2021 MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL 2021 Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains ACL 2021 Mirror Descent View for Neural Network Quantization AISTATS 2021 MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing ICCV 2021 Model-Contrastive Federated Learning CVPR 2021 MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding EMNLP 2021 Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders EACL 2021 MultiLink: Multi-Class Structure Recovery via Agglomerative Clustering and Model Selection CVPR 2021 Multi-Scale Aligned Distillation for Low-Resolution Detection CVPR 2021 Network Pruning via Performance Maximization CVPR 2021 Network Quantization With Element-Wise Gradient Scaling CVPR 2021 NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application EMNLP 2021 NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration CVPR 2021 Online Multi-Granularity Distillation for GAN Compression ICCV 2021 Only Train Once: A One-Shot Neural Network Training And Pruning Framework NeurIPS 2021 On the Limits of Minimal Pairs in Contrastive Evaluation EMNLP 2021 On the Predictability of Pruning Across Scales ICML 2021