Fetching the paper…

Reading the bibliography…

2015

Understanding Intra-Class Knowledge Inside CNN

Wei, Donglai, Zhou, Bolei, Torrabla, Antonio et al.

Original
PDF
Post on X

Understand

Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization.

In this work, we instead visualize the intra-class knowledge inside CNN to better understand how an object class is represented in the fully-connected layers.
To invert the intra-class knowledge into more interpretable images, we propose a non-parametric patch prior upon previous CNN visualization models.
With it, we show how different "styles" of templates for an object class are organized by CNN in terms of location and content, and represented in a hierarchical and ensemble way.

Understanding Intra-Class Knowledge Inside CNN · Around

Built on

Gradient-based learning applied to document recognition
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner · 1998
Earlier work this paper cites.
Patchmatch: a randomized correspondence algorithm for structural image editing
C. Barnes, E. Shechtman, A. Finkelstein, and D. Goldman · 2009
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009
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.
Understanding dropout
P. Baldi and P. J. Sadowski · 2013
Earlier work this paper cites.

Similar

Intriguing properties of neural networks
Original
C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, and R. Fergus · 2013
Cited alongside, same era.
Analyzing the performance of multilayer neural networks for object recognition
P. Agrawal, R. Girshick, and J. Malik · 2014
Cited alongside, same era.
Do convnets learn correspondence?
J. L. Long, N. Zhang, and T. Darrell · 2014
Cited alongside, same era.
Deep inside convolutional networks: Visualising image classification models and saliency maps
K. Simonyan, A. Vedaldi, and A. Zisserman · 2014
Cited alongside, same era.

Then

Visualizing and understanding convolutional networks
M. D. Zeiler and R. Fergus · 2014
Later among the works it cites.
Object detectors emerge in deep scene cnns
Original
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba · 2014
Later among the works it cites.
Understanding deep image representations by inverting them
A. Mahendran and A. Vedaldi · 2015
Closest in time.
Discovering states and transformations in image collections
J. L. P. Isola and E. Adelson · 2015
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…