Model Compression

Scalable Differential Privacy With Sparse Network Finetuning CVPR 2021 Searching by Generating: Flexible and Efficient One-Shot NAS With Architecture Generator CVPR 2021 Self-Born Wiring for Neural Trees ICCV 2021 Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching AAAI 2021 Shrinking Bigfoot: Reducing wav2vec 2.0 footprint EMNLP 2021 Simple and Effective Stochastic Neural Networks AAAI 2021 Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval EMNLP 2021 Slimmable Compressive Autoencoders for Practical Neural Image Compression CVPR 2021 SmallER: Scaling Neural Entity Resolution for Edge Devices Interspeech 2021 SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System Interspeech 2021 Specializing Multilingual Language Models: An Empirical Study EMNLP 2021 Step-Ahead Error Feedback for Distributed Training with Compressed Gradient AAAI 2021 Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks AAAI 2021 Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor ACL 2021 Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021 Teachers Do More Than Teach: Compressing Image-to-Image Models CVPR 2021 TenTrans High-Performance Inference Toolkit for WMT2021 Efficiency Task EMNLP 2021 Text Anchor Based Metric Learning for Small-Footprint Keyword Spotting Interspeech 2021 The Elastic Lottery Ticket Hypothesis NeurIPS 2021 The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation EMNLP 2021 The NiuTrans System for the WMT 2021 Efficiency Task EMNLP 2021 Towards Compact CNNs via Collaborative Compression CVPR 2021 Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021 Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices IJCAI 2021 Towards Faster Deep Collaborative Filtering via Hierarchical Decision Networks AAAI 2021