SOTAVerified

Neural Network Compression

Papers

Showing 126–150 of 193 papers

TitleStatusHype
Grokking as Compression: A Nonlinear Complexity Perspective—0
Guaranteed Quantization Error Computation for Neural Network Model Compression—0
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM—0
HEMP: High-order Entropy Minimization for neural network comPression—0
How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?—0
Hybrid Tensor Decomposition in Neural Network Compression—0
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing—0
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration—0
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition—0
Linearity-based neural network compression—0
Compressing 3DCNNs Based on Tensor Train Decomposition—0
Low-Rank Matrix Approximation for Neural Network Compression—0
Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner—0
MINT: Deep Network Compression via Mutual Information-based Neuron Trimming—0
Partial Binarization of Neural Networks for Budget-Aware Efficient Learning—0
MLPrune: Multi-Layer Pruning for Automated Neural Network Compression—0
Model Compression Methods for YOLOv5: A Review—0
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—0
MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression—0
MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compression—0
Multi-head Knowledge Distillation for Model Compression—0
Filter Distillation for Network Compression—0
Exact Backpropagation in Binary Weighted Networks with Group Weight TransformationsCode0
Neural Network Compression Using Higher-Order Statistics and AuxiliaryReconstruction LossesCode0
Efficient Neural Network CompressionCode0
Show:102550
← PrevPage 6 of 8Next →

No leaderboard results yet.