Distiller 관련 논문 리스트

난 그냥 딥러닝 모델을 Edge에서 빨리 돌리고 싶을 뿐인데 배워야 할게 너무 많다.
Distiller에서 reference하는 논문 자체도 어마어마하게 많으니.. 이 리스트부터 정리하려고 한다.

-	이름	연도	태그
1	Learning both Weights and Connections for Efficient Neural Networks	2015	Pruning
2	Pruning Filters for Efficient ConvNets	2017	Pruning
3	Deep Learning	2017	Regularization
4	DSD: Dense-Sparse-Dense Training for Deep Neural Networks,	2017	Regularization
5	Exploring the Regularity of Sparse Structure in Convolutional Neural Networks	2017	Regularization
6	Structured pruning of deep convolutional neural networks	2015	Regularization
7	High-Performance Hardware for Machine Learning		Quantization
8	Deep Compression : Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding	2016
9	XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks	2016	Quantization
10	Training deep neural networks with low precision multiplications		Quantization
11	Ristretto: A Framework for Empirical Study of Resource-Efficient Inference in Convolutional Neural Networks.	2018	Quantization
12	8-bit Inference with TensorRT	2017	Quantization
13	DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients		Quantization
14	Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights		Quantization
15	WRPN: Wide Reduced-Precision Networks		Quantization
16	PACT: Parameterized Clipping Activation for Quantized Neural Networks		Quantization
17	Towards Accurate Binary Convolutional Neural Network		Quantization
18	Learning both Weights and Connections for Efficient Neural Network		Quantization
19	Ternary Weight Networks		Quantization
20	Trained Ternary Quantization		Quantization
21	Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation		Quantization
22	Neural Networks for Machine Learning		Quantization
23	Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference		Quantization
24	Quantizing deep convolutional networks for efficient inference: A whitepaper		Quantization
25	ACIQ: Analytical Clipping for Integer Quantization of neural networks		Quantization
26	Model Compression		Knowledge Distillation
27	Distilling the Knowledge in a Neural Network		Knowledge Distillation
28	Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks		Knowledge Distillation
29	Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy		Knowledge Distillation
30	Model compression via distillation and quantization		Knowledge Distillation
31	N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning	32	Knowledge Distillation
33	Faster gaze prediction with dense networks and Fisher pruning		Knowledge Distillation

마지막 업데이트 : 2021-05-13