2017

Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions

Wu, Bichen, Wan, Alvin, Yue, Xiangyu et al.

Understand

Neural networks rely on convolutions to aggregate spatial information.

However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadratically with respect to kernel size.
In this paper, we present a parameter-free, FLOP-free "shift" operation as an alternative to spatial convolutions.
We fuse shifts and point-wise convolutions to construct end-to-end trainable shift-based modules, with a hyperparameter characterizing the tradeoff between accuracy and efficiency.

Built on

Face recognition in unconstrained videos with matched background similarity
L. Wolf, T. Hassner, and I. Maoz · 2011
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
A. Krizhevsky, I. Sutskever, and G. E. Hinton · 2012
Earlier work this paper cites.
Caffe: Convolutional architecture for fast feature embedding
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell · 2014
Earlier work this paper cites.
Microsoft COCO: common objects in context
Original
T. Lin, M. Maire, S. J. Belongie, L. D. Bourdev, R. B. Girshick, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick · 2014
Earlier work this paper cites.
Very deep convolutional networks for large-scale image recognition
Original
K. Simonyan and A. Zisserman · 2014
Earlier work this paper cites.
A neural algorithm of artistic style
Original
L. A. Gatys, A. S. Ecker, and M. Bethge · 2015
Earlier work this paper cites.
Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding
Original
S. Han, H. Mao, and W. J. Dally · 2015
Earlier work this paper cites.
Learning both weights and connections for efficient neural networks
Original
S. Han, J. Pool, J. Tran, and W. J. Dally · 2015
Earlier work this paper cites.
Deep face recognition
O. M. Parkhi, A. Vedaldi, and A. Zisserman · 2015
Earlier work this paper cites.
ImageNet Large Scale Visual Recognition Challenge
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei · 2015
Earlier work this paper cites.

Similar

Going deeper with convolutions
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich · 2015
Cited alongside, same era.
Xception: Deep learning with depthwise separable convolutions
Original
F. Chollet · 2016
Cited alongside, same era.
Ms-celeb-1m: Challenge of recognizing one million celebrities in the real world
Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao · 2016
Cited alongside, same era.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Cited alongside, same era.
Rethinking the inception architecture for computer vision
G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller · 2016
Cited alongside, same era.
Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size
Original
F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer · 2016
Cited alongside, same era.
Perceptual losses for real-time style transfer and super-resolution
Original
J. Johnson, A. Alahi, and F. Li · 2016
Cited alongside, same era.
Local binary convolutional neural networks
Original
F. Juefei-Xu, V. N. Boddeti, and M. Savvides · 2016
Cited alongside, same era.
Xnor-net: Imagenet classification using binary convolutional neural networks
M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi · 2016
Cited alongside, same era.
Facenet: A unified embedding for face recognition and clustering
F. Schroff, D. Kalenichenko, and J. Philbin
Cited in the paper.

Then

Rethinking the inception architecture for computer vision
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna · 2016
Later among the works it cites.
Instance normalization: The missing ingredient for fast stylization
Original
D. Ulyanov, A. Vedaldi, and V. S. Lempitsky · 2016
Later among the works it cites.
A discriminative feature learning approach for deep face recognition
Y. Wen, K. Zhang, Z. Li, and Y. Qiao · 2016
Later among the works it cites.
Aggregated residual transformations for deep neural networks
Original
S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He · 2016
Later among the works it cites.
Joint face detection and alignment using multitask cascaded convolutional networks
K. Zhang, Z. Zhang, Z. Li, and Y. Qiao · 2016
Later among the works it cites.
Mobilenets: Efficient convolutional neural networks for mobile vision applications
Original
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam · 2017
Closest in time.
A compact DNN: approaching googlenet-level accuracy of classification and domain adaptation
Original
C. Wu, W. Wen, T. Afzal, Y. Zhang, Y. Chen, and H. Li · 2017
Closest in time.
On compressing deep models by low rank and sparse decomposition
X. Yu, T. Liu, X. Wang, and D. Tao · 2017
Closest in time.
Shufflenet: An extremely efficient convolutional neural network for mobile devices
Original
X. Zhang, X. Zhou, M. Lin, and J. Sun · 2017
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…