2017

Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly

Xian, Yongqin, Lampert, Christoph H., Schiele, Bernt et al.

Understand

Due to the importance of zero-shot learning, i.e.

classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily.
We argue that it is time to take a step back and to analyze the status quo of the area.
The purpose of this paper is three-fold.

Built on

R. H. Bartels and G. Stewart, “Solution of the matrix equation ax+ xb= c [f4],”
1972
Earlier work this paper cites.
G. A. Miller, “Wordnet: a lexical database for english,”
1995
Earlier work this paper cites.
T. Joachims, “Optimizing search engines using clickthrough data,” in
2002
Earlier work this paper cites.
D. G. Lowe, “Distinctive image features from scale-invariant keypoints,”
2004
Earlier work this paper cites.
D. Zhou, O. Bousquet, T. N. Lal, J. Weston, and B. Schölkopf, “Learning with local and global consistency,” in
2004
Earlier work this paper cites.
I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, “Large margin methods for structured and interdependent output variables,”
2005
Earlier work this paper cites.
H. Larochelle, D. Erhan, and Y. Bengio, “Zero-data learning of new tasks,” in
2008
Earlier work this paper cites.
A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth, “Describing objects by their attributes,”
2009
Earlier work this paper cites.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A Large-Scale Hierarchical Image Database,” in
2009
Earlier work this paper cites.
M. Palatucci, D. Pomerleau, G. E. Hinton, and T. M. Mitchell, “Zero-shot learning with semantic output codes,” in
2009
Earlier work this paper cites.
N. Usunier, D. Buffoni, and P. Gallinari, “Ranking with ordered weighted pairwise classification,” in
2009
Earlier work this paper cites.
O. Chapelle, B. Scholkopf, and A. Zien, “Semi-supervised learning,”
2009
Earlier work this paper cites.
X. Yu and Y. Aloimonos, “Attribute-based transfer learning for object categorization with zero or one training example,” in
2010
Earlier work this paper cites.
P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, and P. Perona, “Caltech-UCSD Birds 200,” Caltech, Tech. Rep. CNS-TR-2010-001, 2010
2010
Earlier work this paper cites.
M. Rohrbach, M. Stark, G. Szarvas, I. Gurevych, and B. Schiele, “What helps where–and why? semantic relatedness for knowledge transfer,” in
2010
Earlier work this paper cites.
M. Rohrbach, M. Stark, and B.Schiele, “Evaluating knowledge transfer and zero-shot learning in a large-scale setting,” in
2011
Earlier work this paper cites.
J. Weston, S. Bengio, and N. Usunier, “Wsabie: Scaling up to large vocabulary image annotation,” in
2011
Earlier work this paper cites.
G. Patterson and J. Hays, “Sun attribute database: Discovering, annotating, and recognizing scene attributes,” in
2012
Earlier work this paper cites.
P. Kankuekul, A. Kawewong, S. Tangruamsub, and O. Hasegawa, “Online incremental attribute-based zero-shot learning,” in
2012
Earlier work this paper cites.
T. Mensink, J. Verbeek, F. Perronnin, and G. Csurka, “Metric learning for large scale image classification: Generalizing to new classes at near-zero cost,”
2012
Earlier work this paper cites.
C. Lampert, H. Nickisch, and S. Harmeling, “Attribute-based classification for zero-shot visual object categorization,” in
2013
Earlier work this paper cites.
A. Frome, G. S. Corrado, J. Shlens, S. Bengio, J. Dean, M. A. Ranzato, and T. Mikolov, “Devise: A deep visual-semantic embedding model,” in
2013
Earlier work this paper cites.
Z. Akata, F. Perronnin, Z. Harchaoui, and C. Schmid, “Label embedding for attribute-based classification,” in
2013
Earlier work this paper cites.
R. Socher, M. Ganjoo, C. D. Manning, and A. Ng, “Zero-shot learning through cross-modal transfer,” in
2013
Earlier work this paper cites.
T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” in
2013
Earlier work this paper cites.
M. Rohrbach, S. Ebert, and B. Schiele, “Transfer learning in a transductive setting,” in
2013
Earlier work this paper cites.

Similar

M. Elhoseiny, B. Saleh, and A. Elgammal, “Write a classifier: Zero-shot learning using purely textual descriptions,” in
2013
Cited alongside, same era.
W. J. Scheirer, A. Rocha, A. Sapkota, and T. E. Boult, “Towards open set recognition,”
2013
Cited alongside, same era.
S. Garcia and F. Herrera, “An extension on“statistical comparisons of classifiers over multiple data sets”for all pairwise comparisons,”
2013
Cited alongside, same era.
M. Norouzi, T. Mikolov, S. Bengio, Y. Singer, J. Shlens, A. Frome, G. Corrado, and J. Dean, “Zero-shot learning by convex combination of semantic embeddings,” in
2014
Cited alongside, same era.
J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell, “Decaf: A deep convolutional activation feature for generic visual recognition.” in
2014
Cited alongside, same era.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,”
Original
2014
Cited alongside, same era.
D. Jayaraman and K. Grauman, “Zero-shot recognition with unreliable attributes,” in
2014
Cited alongside, same era.
T. Mensink, E. Gavves, and C. G. Snoek, “Costa: Co-occurrence statistics for zero-shot classification,” in
2014
Cited alongside, same era.
S. Antol, C. L. Zitnick, and D. Parikh, “Zero-shot learning via visual abstraction,” in
2014
Cited alongside, same era.
J. Pennington, R. Socher, and C. D. Manning, “Glove: Global vectors for word representation,” in
2014
Cited alongside, same era.
L. Jain, W. Scheirer, and T. Boult, “Multi-class open set recognition using probability of inclusion,” in
2014
Cited alongside, same era.
Y. Fujiwara and G. Irie, “Efficient label propagation,” in
2014
Cited alongside, same era.

Then

S. Changpinyo, W.-L. Chao, B. Gong, and F. Sha, “Synthesized classifiers for zero-shot learning,” in
2016
Later among the works it cites.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in
2016
Later among the works it cites.
Z. Al-Halah, M. Tapaswi, and R. Stiefelhagen, “Recovering the missing link: Predicting class-attribute associations for unsupervised zero-shot learning,” in
2016
Later among the works it cites.
Z. Akata, F. Perronnin, Z. Harchaoui, and C. Schmid, “Label-embedding for image classification,”
2016
Later among the works it cites.
R. Qiao, L. Liu, C. Shen, and A. van den Hengel, “Less is more: Zero-shot learning from online textual documents with noise suppression,” in
2016
Later among the works it cites.
M. Bucher, S. Herbin, and F. Jurie, “Improving semantic embedding consistency by metric learning for zero-shot classiffication,” in
2016
Later among the works it cites.
Z. Zhang and V. Saligrama, “Zero-shot learning via joint semantic similarity embedding,” in
2016
Later among the works it cites.
Z. Akata, M. Malinowski, M. Fritz, and B. Schiele, “Multi-cue zero-shot learning with strong supervision,” in
2016
Later among the works it cites.
T. Mukherjee and T. Hospedales, “Gaussian visual-linguistic embedding for zero-shot recognition,” in
2016
Later among the works it cites.
Y. Fu and L. Sigal, “Semi-supervised vocabulary-informed learning,” in
2016
Later among the works it cites.
Z. Zhang and V. Saligrama, “Zero-shot recognition via structured prediction,” in
2016
Later among the works it cites.
S. Reed, Z. Akata, H. Lee, and B. Schiele, “Learning deep representations of fine-grained visual descriptions,” in
2016
Later among the works it cites.
H. Zhang, X. Shang, W. Yang, H. Xu, H. Luan, and T.-S. Chua, “Online collaborative learning for open-vocabulary visual classifiers,” in
2016
Later among the works it cites.
A. Bendale and T. E. Boult, “Towards open set deep networks,” in
2016
Later among the works it cites.
W.-L. Chao, S. Changpinyo, B. Gong, and F. Sha, “An empirical study and analysis of generalized zero-shot learning for object recognition in the wild,” in
2016
Later among the works it cites.
X. Xu, Y. Yang, D. Zhang, H. T. Shen, and J. Song, “Matrix tri-factorization with manifold regularizations for zero-shot learning,” in
2017
Closest in time.
Z. Ding, M. Shao, and Y. Fu, “Low-rank embedded ensemble semantic dictionary for zero-shot learning,” in
2017
Closest in time.
E. Kodirov, T. Xiang, and S. Gong, “Semantic autoencoder for zero-shot learning,” in
2017
Closest in time.
L. Zhang, T. Xiang, and S. Gong, “Learning a deep embedding model for zero-shot learning,” in
2017
Closest in time.
S. Changpinyo, W.-L. Chao, and F. Sha, “Predicting visual exemplars of unseen classes for zero-shot learning,”
2017
Closest in time.
Y. Long, L. Liu, L. Shao, F. Shen, G. Ding, and J. Han, “From zero-shot learning to conventional supervised classification: Unseen visual data synthesis,” in
2017
Closest in time.
V. K. Verm and P. Rai, “A simple exponential family framework for zero-shot learning,” in
2017
Closest in time.
Y. Li and D. Wang, “Zero-shot learning with generative latent prototype model,”
Original
2017
Closest in time.
N. Karessli, Z. Akata, B. Schiele, and A. Bulling, “Gaze embeddings for zero-shot image classification,” in
2017
Closest in time.
M. Ye and Y. Guo, “Zero-shot classification with discriminative semantic representation learning,” in
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…