← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

TRQ: Ternary Neural Networks With Residual Quantization AAAI 2021
TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning AAAI 2021
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques AAAI 2021
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021
Step-Ahead Error Feedback for Distributed Training with Compressed Gradient AAAI 2021
FracBits: Mixed Precision Quantization via Fractional Bit-Widths AAAI 2021
Any-Precision Deep Neural Networks AAAI 2021
Accelerating Neural Machine Translation with Partial Word Embedding Compression AAAI 2021
Deeplite NeutrinoTM: A BlackBox Framework for Constrained Deep Learning Model Optimization AAAI 2021
Shallow-UWnet: Compressed Model for Underwater Image Enhancement (Student Abstract) AAAI 2021
Mining Intelligent Patterns using SVAC for Precision Agriculture and Optimizing Irrigation (Student Abstract) AAAI 2021
A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices AAAI 2021
DeepReDuce: ReLU Reduction for Fast Private Inference ICML 2021
Accurate Post Training Quantization With Small Calibration Sets ICML 2021
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021
A Unified Lottery Ticket Hypothesis for Graph Neural Networks ICML 2021
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision ICML 2021
Zero-Shot Adversarial Quantization CVPR 2021
ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic CVPR 2021
Diverse Branch Block: Building a Convolution as an Inception-Like Unit CVPR 2021
Post-Hoc Uncertainty Calibration for Domain Drift Scenarios CVPR 2021
Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-End Speech Recognition INTERSPEECH 2021
PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation INTERSPEECH 2021
Extremely Low Footprint End-to-End ASR System for Smart Device INTERSPEECH 2021
KSM: Fast Multiple Task Adaption via Kernel-Wise Soft Mask Learning CVPR 2021