Model Compression

Convolutional Neural Network Pruning With Structural Redundancy Reduction CVPR 2021 Decomposable-Net: Scalable Low-Rank Compression for Neural Networks IJCAI 2021 Decoupled Dynamic Filter Networks CVPR 2021 Deep Learning meets Projective Clustering ICLR 2021 Degree-Quant: Quantization-Aware Training for Graph Neural Networks ICLR 2021 Demystifying and Generalizing BinaryConnect NeurIPS 2021 Densely Guided Knowledge Distillation Using Multiple Teacher Assistants ICCV 2021 Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution ICML 2021 Direction is what you need: Improving Word Embedding Compression in Large Language Models ACL 2021 Dirichlet Pruning for Convolutional Neural Networks AISTATS 2021 Distance-Aware Quantization ICCV 2021 Distilling Knowledge via Knowledge Review CVPR 2021 DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks NeurIPS 2021 DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch AAAI 2021 DPOQ: Dynamic Precision Onion Quantization ACML 2021 Dynamic Slimmable Network CVPR 2021 Effectiveness of Arbitrary Transfer Sets for Data-Free Knowledge Distillation WACV 2021 Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021 Efficient Attentions for Long Document Summarization NAACL 2021 EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation EMNLP 2021 Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators ACL 2021 Exploration and Estimation for Model Compression ICCV 2021 Extremely Small BERT Models from Mixed-Vocabulary Training EACL 2021 Factorization-Aware Training of Transformers for Natural Language Understanding on the Edge Interspeech 2021 Faster Depth-Adaptive Transformers AAAI 2021