Papers with Code 아카이브
Neural Network Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 4
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Teacher-Class Network: A Neural Network Compression Mechanism
DP-Net: Dynamic Programming Guided Deep Neural Network Compression
MINT: Deep Network Compression via Mutual Information-based Neuron Trimming
The continuous categorical: a novel simplex-valued exponential family
Neural Network Compression Framework for fast model inference
REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild
Quantisation and Pruning for Neural Network Compression and Regularisation
ZeroQ: A Novel Zero Shot Quantization Framework
Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis
Compressing 3DCNNs Based on Tensor Train Decomposition
A Programmable Approach to Neural Network Compression
Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
A Comparative Study of Neural Network Compression
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
Deep Neural Network Compression for Image Classification and Object Detection
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems
XNOR-Net++: Improved Binary Neural Networks
Forward and Backward Information Retention for Accurate Binary Neural Networks
Learning Filter Basis for Convolutional Neural Network Compression
DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
Similarity-Preserving Knowledge Distillation
Weight Normalization based Quantization for Deep Neural Network Compression
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
Learning Sparse Networks Using Targeted Dropout
DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression
SCANN: Synthesis of Compact and Accurate Neural Networks
Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network
Data-Free Learning of Student Networks
Online Multi-target regression trees with stacked leaf models
MUSCO: Multi-Stage Compression of neural networks
Cascaded Projection: End-to-End Network Compression and Acceleration
Focused Quantization for Sparse CNNs
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.