2017

Deeper, Broader and Artier Domain Generalization

Li, Da, Yang, Yongxin, Song, Yi-Zhe et al.

Understand

The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain.

Domain generalization (DG) has a clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training.
For example recognition in sketch images, which are distinctly more abstract and rarer than photos.
Nevertheless, DG methods have primarily been evaluated on photo-only benchmarks focusing on alleviating the dataset bias where both problems of domain distinctiveness and data sparsity can be minimal.

Built on

Some mathematical notes on three-mode factor analysis
L. R. Tucker · 1966
Earlier work this paper cites.
A multilinear singular value decomposition
L. D. Lathauwer, B. D. Moor, and J. Vandewalle · 2000
Earlier work this paper cites.
Visualizing data using t-sne
L. v. d. Maaten and G. Hinton · 2008
Earlier work this paper cites.
Adapting visual category models to new domains
K. Saenko, B. Kulis, M. Fritz, and T. Darrell · 2010
Earlier work this paper cites.
Unbiased look at dataset bias
A. Torralba and A. A. Efros · 2011
Earlier work this paper cites.
How do humans sketch objects?
M. Eitz, J. Hays, and M. Alexa · 2012
Earlier work this paper cites.
Geodesic flow kernel for unsupervised domain adaptation
B. Gong, Y. Shi, F. Sha, and K. Grauman · 2012
Earlier work this paper cites.
Undoing the damage of dataset bias
A. Khosla, T. Zhou, T. Malisiewicz, A. Efros, and A. Torralba · 2012
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.
Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias
C. Fang, Y. Xu, and D. N. Rockmore · 2013
Earlier work this paper cites.
Domain generalization via invariant feature representation
K. Muandet, D. Balduzzi, and B. Scholkopf · 2013
Earlier work this paper cites.
Decaf: A deep convolutional activation feature for generic visual recognition
J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell · 2014
Earlier work this paper cites.

Similar

Learning graphs to model visual objects across different depictive styles
Q. Wu, H. Cai, and P. Hall · 2014
Cited alongside, same era.
Exploiting low-rank structure from latent domains for domain generalization
Z. Xu, W. Li, L. Niu, and D. Xu · 2014
Cited alongside, same era.
How transferable are features in deep neural networks?
J. Yosinski, J. Clune, Y. Bengio, and H. Lipson · 2014
Cited alongside, same era.
Face painting: querying art with photos
E. J. Crowley, O. M. Parkhi, and A. Zisserman · 2015
Cited alongside, same era.
Unsupervised domain adaptation by backpropagation
Y. Ganin and V. Lempitsky · 2015
Cited alongside, same era.
Domain generalization for object recognition with multi-task autoencoders
M. Ghifary, W. Bastiaan Kleijn, M. Zhang, and D. Balduzzi · 2015
Cited alongside, same era.
Speeding-up convolutional neural networks using fine-tuned cp-decomposition
V. Lebedev, Y. Ganin, M. Rakhuba, I. Oseledets, and V. Lempitsky · 2015
Cited alongside, same era.
Learning transferable features with deep adaptation networks
M. Long, Y. Cao, J. Wang, and M. I. Jordan · 2015
Cited alongside, same era.
Gated networks: an inventory
O. Sigaud, C. Masson, D. Filliat, and F. Stulp · 2015
Cited alongside, same era.
Learning feed-forward one-shot learners
L. Bertinetto, J. F. Henriques, J. Valmadre, P. H. S. Torr, and A. Vedaldi · 2016
Cited alongside, same era.
Domain separation networks
K. Bousmalis, G. Trigeorgis, N. Silberman, D. Krishnan, and D. Erhan · 2016
Cited alongside, same era.

Then

The art of detection
A. Z. E. J. Crowley · 2016
Later among the works it cites.
Compression of deep convolutional neural networks for fast and low power mobile applications
Y.-D. Kim, E. Park, S. Yoo, T. Choi, L. Yang, and D. Shin · 2016
Later among the works it cites.
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
A. M. Nguyen, A. Dosovitskiy, J. Yosinski, T. Brox, and J. Clune · 2016
Later among the works it cites.
The sketchy database: learning to retrieve badly drawn bunnies
P. Sangkloy, N. Burnell, C. Ham, and J. Hays · 2016
Later among the works it cites.
Sketch me that shoe
Q. Yu, F. Liu, Y.-Z. Song, T. Xiang, T. M. Hospedales, and C. C. Loy · 2016
Later among the works it cites.
Model-agnostic meta-learning for fast adaptation of deep networks
C. Finn, P. Abbeel, and S. Levine · 2017
Closest in time.
Meta networks
T. Munkhdalai and H. Yu · 2017
Closest in time.
Optimization as a model for few-shot learning
S. Ravi and H. Larochelle · 2017
Closest in time.
Deep spatial-semantic attention for fine-grained sketch-based image retrieval
J. Song, Y. Qian, Y.-Z. Song, T. Xiang, and T. Hospedales · 2017
Closest in time.
Deep multi-task representation learning: A tensor factorisation approach
Y. Yang and T. M. Hospedales · 2017
Closest in time.
Sketch-a-net: A deep neural network that beats humans
Original
Q. Yu, Y. Yang, F. Liu, Y.-Z. Song, T. Xiang, and T. M. Hospedales · 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…