Fetching the paper…
Reading the bibliography…
We show that unsupervised training of latent capsule layers using only the reconstruction loss, without masking to select the correct output class, causes a loss of equivariances and other desirable capsule qualities.
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, Bruno A. and Field, David J · 1997
Earlier work this paper cites.
Gradient-based learning applied to document recognition
LeCun, Yann, Bottou, Léon, Bengio, Yoshua, and Haffner, Patrick · 1998
Earlier work this paper cites.
Method of optimal directions for frame design
Engan, K., Aase, S.O., and Hakon Husoy, J · 1999
Earlier work this paper cites.
Understanding belief propagation and its generalizations
Yedidia, J. S, Freeman, W. T, and Weiss, Y · 2003
Earlier work this paper cites.
Learning methods for generic object recognition with invariance to pose and lighting
LeCun, Yann, Huang, Fu Jie, and Bottou, Léon · 2004
Earlier work this paper cites.
K-Svd : Design of Dictionaries for Sparse Representation
Aharon, Michal, Elad, Michael, and Bruckstein, Alfred M · 2005
Earlier work this paper cites.
Sparse deep belief net model for visual area V2
Lee, Honglak, Ekanadham, Chaitanya, and Ng, Andrew Y · 2007
Earlier work this paper cites.
3D Object Recognition with Deep Belief Nets
Nair, Vinod and Hinton, Geoffrey E · 2009
Earlier work this paper cites.
Why Does Unsupervised Pre-training Help Deep Learning ?
Erhan, Dumitru, Courville, Aaron, and Vincent, Pascal · 2010
Earlier work this paper cites.
Transforming Auto-Encoders
Hinton, Geoffrey E, Krizhevsky, Alex, and Wang, Sida D · 2011
Cited alongside, same era.
Building high-level features using large scale unsupervised learning
Le, Quoc V, Ranzato, Marc’Aurelio, Monga, Rajat, Devin, Matthieu, Chen, Kai, Corrado, Greg S, Dean, Jeff, and Ng, Andrew Y · 2012
Cited alongside, same era.
Makhzani, Alireza and Frey, Brendan · 2013
Cited alongside, same era.
Explaining and Harnessing Adversarial Examples
Goodfellow, Ian J., Shlens, Jonathon, and Szegedy, Christian · 2014
Cited alongside, same era.
Optimizing Neural Networks that Generate Images
Tieleman, Tijmen · 2014
Cited alongside, same era.
Contextual Priming and Feedback for Faster R-CNN
Shrivastava, Abhinav and Gupta, Abhinav · 2016
Later among the works it cites.
Residual Networks Behave Like Ensembles of Relatively Shallow Networks
Veit, Andreas, Wilber, Michael, and Belongie, Serge · 2016
Later among the works it cites.
Broadcasting Convolutional Network
Chang, Simyung, Yang, John, Park, Seonguk, and Kwak, Nojun · 2017
Later among the works it cites.
Computational neuroscience offers hints for more general machine learning
Rawlinson, David and Kowadlo, Gideon · 2017
Later among the works it cites.
Dynamic Routing between Capsules
Sabour, Sara, Frosst, Nicholas, and Hinton, Geoffrey · 2017
Later among the works it cites.
Inception-v4, inception-resnet and the impact of residual connections on learning
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Balduzzi, David, Vanchinathan, Hastagiri, and Buhmann, Joachim · 2015
Cited alongside, same era.
Winner-Take-All Autoencoders
Makhzani, Alireza and Frey, Brendan J · 2015
Cited alongside, same era.
Towards Biologically Plausible Deep Learning
Bengio, Yoshua, Lee, Dong-Hyun, Bornschein, Jorg, Mesnard, Thomas, and Lin, Zhouhan · 2016
Cited alongside, same era.
Adversarial examples in the physical world
Kurakin, Alexey, Goodfellow, Ian, and Bengio, Samy · 2016
Cited alongside, same era.
Szegedy, Christian, Ioffe, Sergey, Vanhoucke, Vincent, and Alemi, Alex · 2017
Later among the works it cites.
Marginalized CNN: Learning Deep Invariant Representations
Zhao, Jian, Li, Jianshu, Zhao, Fang, Yan, Shuicheng, and Feng, Jiashi · 2017
Later among the works it cites.
Proposal of transformation robust attentive convolutional neural network
Asano, Shuhei · 2018
Closest in time.
Matrix capsules with EM routing
Hinton, Geoffrey, Sabour, Sara, and Frosst, Nicholas · 2018
Closest in time.