[최적화] Model Compression 논문 리스트

최적화

요 블로그 주인장 2023. 10. 17. 00:12

2. Learning both Weights and Connections for EfficientNeural Networks

3. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

4. DSD: Dense-Sparse-Dense Training for Deep Neural Networks

5. NISP: Pruning Networks using Neuron Importance Score Propagation

6. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

7. Dynamic Network Surgery for Efficient DNNs

8. Learning Efficient Convolutional Networks through Network Slimming

9. Rethinking the Value of Network Pruning

10. Learning Structured Sparsity in Deep Neural Networks

11. Pruning Filters for Efficient ConvNets

12. Variational Convolutional Neural Network Pruning

13. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

14. Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures

15. Exploring the Regularity of Sparse Structure in Convolutional Neural Networks

16. Scalpel: Customizing DNN pruning to the underlying hardware parallelism

17. Do Deep Nets Really Need to be Deep?

18. CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices

19. Model compression via distillation and quantization

20. Single-shot Network Pruning based on Connection Sensitivity

21. PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration

22. Compression-aware Training of Deep Networks

23. A Signal Propagation Perspective for Pruning Neural Networks at Initialization

Reference

->아직 추가 안함

-> 아직 추가 안함 (2020년 이후 최신 논문)

-> 아직 추가 안함 (2021년 이후 최신 논문)