Model Compression

Towards Memory-Efficient Neural Networks via Multi-Level In Situ Generation ICCV 2021 Training Neural Networks with Fixed Sparse Masks NeurIPS 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 Versatile Verification of Tree Ensembles ICML 2021 Wasserstein Contrastive Representation Distillation CVPR 2021 Weight Distillation: Transferring the Knowledge in Neural Network Parameters ACL 2021 Winning Lottery Tickets in Deep Generative Models AAAI 2021 YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design AAAI 2021 Accuracy Booster: Performance Boosting using Feature Map Re-calibration WACV 2020 AdaBits: Neural Network Quantization With Adaptive Bit-Widths CVPR 2020 Adaptive Loss-Aware Quantization for Multi-Bit Networks CVPR 2020 AdderNet: Do We Really Need Multiplications in Deep Learning? CVPR 2020 Adversarially Robust Distillation AAAI 2020 A Greedy Bit-flip Training Algorithm for Binarized Knowledge Graph Embeddings EMNLP 2020 Analysis of Resource-efficient Predictive Models for Natural Language Processing EMNLP 2020 Analyzing Redundancy in Pretrained Transformer Models EMNLP 2020 AOWS: Adaptive and Optimal Network Width Search With Latency Constraints CVPR 2020 APQ: Joint Search for Network Architecture, Pruning and Quantization Policy CVPR 2020 ASAP: Architecture Search, Anneal and Prune AISTATS 2020 AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates AAAI 2020 Automatically Learning Compact Quality-aware Surrogates for Optimization Problems NeurIPS 2020