Model Compression

Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks AAAI 2021 Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021 Sustainable Modular Debiasing of Language Models EMNLP 2021 Teacher Guided Neural Architecture Search for Face Recognition AAAI 2021 The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization NeurIPS 2021 The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures CVPR 2021 The Lottery Ticket Hypothesis for Object Recognition CVPR 2021 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation EMNLP 2021 Towards Compact CNNs via Collaborative Compression CVPR 2021 Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021 Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure CVPR 2021 Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices IJCAI 2021 Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP 2021 TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning AAAI 2021 Tree-Like Decision Distillation CVPR 2021 Troubleshooting Blind Image Quality Models in the Wild CVPR 2021 TRQ: Ternary Neural Networks With Residual Quantization AAAI 2021 Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval EMNLP 2021 Uncertainty-aware Binary Neural Networks IJCAI 2021 UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings EMNLP 2021 Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021 Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021 Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources CVPR 2021 Weight Distillation: Transferring the Knowledge in Neural Network Parameters ACL 2021