← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings EMNLP 2021
Shrinking Bigfoot: Reducing wav2vec 2.0 footprint EMNLP 2021
Findings of the WMT 2021 Shared Task on Efficient Translation EMNLP 2021
Papago’s Submission for the WMT21 Quality Estimation Shared Task EMNLP 2021
The Elastic Lottery Ticket Hypothesis NIPS 2021
Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021
Network Quantization With Element-Wise Gradient Scaling CVPR 2021
Dynamic Slimmable Network CVPR 2021
QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks CVPR 2021
Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021
ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic CVPR 2021
Slimmable Compressive Autoencoders for Practical Neural Image Compression CVPR 2021
Improving Accuracy of Binary Neural Networks Using Unbalanced Activation Distribution CVPR 2021
Towards Compact CNNs via Collaborative Compression CVPR 2021
General Instance Distillation for Object Detection CVPR 2021
Compatibility-Aware Heterogeneous Visual Search CVPR 2021
Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021
Wasserstein Contrastive Representation Distillation CVPR 2021
Learnable Companding Quantization for Accurate Low-Bit Neural Networks CVPR 2021
BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021
Model-Contrastive Federated Learning CVPR 2021
Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021
Teachers Do More Than Teach: Compressing Image-to-Image Models CVPR 2021
FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection JMLR 2021
Learning a Neural Diff for Speech Models INTERSPEECH 2021