← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

Revisiting Random Channel Pruning for Neural Network Compression CVPR 2022
Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error CVPR 2022
Evaluation-Oriented Knowledge Distillation for Deep Face Recognition CVPR 2022
Slimmable Domain Adaptation CVPR 2022
3DAC: Learning Attribute Compression for Point Clouds CVPR 2022
When To Prune? A Policy Towards Early Structural Pruning CVPR 2022
Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-Learning CVPR 2022
Localization Distillation for Dense Object Detection CVPR 2022
Compressing Models With Few Samples: Mimicking Then Replacing CVPR 2022
BMCook: A Task-agnostic Compression Toolkit for Big Models EMNLP 2022
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training ICML 2022
Analyzing and Mitigating Interference in Neural Architecture Search ICML 2022
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models EMNLP 2022
Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models EMNLP 2022
Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models NAACL 2022
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline NAACL 2022
Adaptable Adapters NAACL 2022
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval NAACL 2022
A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022
Maximum Bayes Smatch Ensemble Distillation for AMR Parsing NAACL 2022
Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training NIPS 2022
Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise NIPS 2022
Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks NIPS 2022
The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model NIPS 2022
Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT EMNLP 2022