← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

Distribution-Aware Adaptive Multi-Bit Quantization CVPR 2021
Joint-DetNAS: Upgrade Your Detector With NAS, Pruning and Dynamic Distillation CVPR 2021
CARTL: Cooperative Adversarially-Robust Transfer Learning ICML 2021
Accurate Post Training Quantization With Small Calibration Sets ICML 2021
1-bit Adam: Communication Efficient Large-Scale Training with Adam’s Convergence Speed ICML 2021
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework ICML 2021
HAWQ-V3: Dyadic Neural Network Quantization ICML 2021
Binary Graph Neural Networks CVPR 2021
ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting ICCV 2021
Distilling Linguistic Context for Language Model Compression EMNLP 2021
Learning Compact Metrics for MT EMNLP 2021
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications EMNLP 2021
FracBits: Mixed Precision Quantization via Fractional Bit-Widths AAAI 2021
Anytime Inference with Distilled Hierarchical Neural Ensembles AAAI 2021
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques AAAI 2021
TRQ: Ternary Neural Networks With Residual Quantization AAAI 2021
Knowledge Distillation for Singing Voice Detection INTERSPEECH 2021
FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications INTERSPEECH 2021
SmallER: Scaling Neural Entity Resolution for Edge Devices INTERSPEECH 2021
Disfluency Detection with Unlabeled Data and Small BERT Models INTERSPEECH 2021
SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System INTERSPEECH 2021
FRILL: A Non-Semantic Speech Embedding for Mobile Devices INTERSPEECH 2021
Text Anchor Based Metric Learning for Small-Footprint Keyword Spotting INTERSPEECH 2021
Energy-Friendly Keyword Spotting System Using Add-Based Convolution INTERSPEECH 2021