A New Light-Weight and Efficient Convolutional Neural Network Using Fast Discrete Cosine Transform

목차 (Table of Contents)

• 요약
• Abstract
• 1. 서론
• 2. 관련 연구
• 3. 제안 방법
• 4. 분석
• 5. 결론
• References

참고문헌 (Reference)

1 Zhang, Xiangyu, "Shufflenet: An extremely efficient convolutional neural network for mobile devices" 6848-6856, 2018

2 Ma, Ningning, "Shufflenet v2 : Practical guidelines for efficient cnn architecture design" 116-131, 2018

3 Shwartz-Ziv, Ravid, "Opening the black box of deep neural networks via information"

4 Sandler, Mark, "Mobilenetv2: Inverted residuals and linear bottlenecks" 4510-4520, 2018

5 A. G. Howard, "Mobilenets : Efficient convolutional neural networks for mobile vision applications"

6 Tan, Mingxing, "Mnasnet : Platform-aware neural architecture search for mobile" 2820-2828, 2019

7 Tsung-Yi Lin, "Microsoft coco : Common objects in context" 740-755, 2014

8 Krizhevsky, Alex, "Learning multiple layers of features from tiny images" University of Toronto 2009

9 Raid, A. M., "Jpeg image compression using discrete cosine transform-A survey"

10 Szegedy, Christian, "Inception-v4, inceptionresnet and the impact of residual connections on learning" 2017

11 Jia Deng, "Imagenet: A large-scale hierarchical image database" 248-255, 2009

12 A. Krizhevsky, "Imagenet classification with deep convolutional neural networks" 1097-1105, 2012

13 Wu, Bichen, "Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search" 10734-10742, 2019

14 N. Ahmed, "Discrete cosine transform" C-25 : 90-93, 1974

15 Huang, Gao, "Densely Connected Convolutional Networks" 4700-4708, 2017

16 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016

17 Ioffe, Sergey, "Batch normalization:Accelerating deep network training by reducing internal covariate shift"

18 Canziani, Alfredo, "An analysis of deep neural network models for practical applications"

19 J. Makhoul, "A fast cosine transform in one and two dimensions" 28 (28): 27-34, 1980