Model Compression Paper List Read

2019년 목표 50편 정독하기, 10개 Pytorch, tensorflow로 구현해보기(...)

 

최초 작성 (2019.10.08)

1차 수정 (2019.10.16)

2차 수정 (2019.10.22)

3차 수정 (2019.10.30)

4차 수정 (2019.11.07)

5차 수정 (2019.11.17)

6차 수정 (2019.11.26)

7차 수정 (2019.12.04)

8차 수정 (2019.12.26)

 

공부한 것

Optimal Brain Damage	NIPS 1989
Learning both Weights and  Connections for Efficient Neural Networks	NIPS 2015
Deep Compression: Comressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding	ICLR 2016 (oral)
DSD: Dense-Sparse-Dense Training for Deep Neural Networks	ICLR 2017
NISP: Pruning Networks using Neural Importance Score Propagation	CVPR 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks	ICLR 2019 (best paper)
Dynamic Network Surgery for Efficient DNNs	NIPS 2016
Learning Efficient Convolutional Networks through Network Slimming	ICCV 2017
Rethinking the Value of Network Pruning	ICLR 2019
Learning Structured Sparsity in Deep Neural Networks	NIPS 2016
Pruning Filters for Efficient ConvNets	ICLR 2017
Variational Convolutional Neural Network Purning	CVPR 2019
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration	CVPR 2019 (oral)
Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures	CVPR 2017
Exploring the Regularity of Sparse Structure in Convolutional Neural Networks	NIPS 2017
Scalpel: Customizing DNN pruning to the underlying hardware parallelism	ISCA 2017
Do Deep Nets Really Need to be Deep?	NIPS 2014
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-Circulant Weight Matrices	MICRO 2017
Model Compression via Distillation and Quantization	ICLR 2018
SNIP: Single-shot Network Pruning based on Connection Sensitivity	ICLR 2019
PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration	SC 2019 (best paper finialist)
Compression-aware Training of Deep Networks	NIPS 2017
A Signal Propagation Perspective for Pruning Neural Networks at Initialization	ICLR 2020 (spotlight)