Few-shot learning in deep networks through global prototyping

Neural Networks

Volumn 94, Issue , 2017, Pages 159-172

  Blaes, Sebastian ^a   Burwick, Thomas ^a,b  

^a FRANKFURT INSTITUTE FOR ADVANCED STUDIES   (Germany)

^b MAASTRICHT UNIVERSITY   (Netherlands)

Author keywords

Convolutional Neural Networks; Deep Learning; Few Shot Learning; Object Recognition; Transfer Learning

Indexed keywords

CONVOLUTION; DEEP LEARNING; LEARNING SYSTEMS; NEURAL NETWORKS; OBJECT RECOGNITION;

CLASSIFICATION PERFORMANCE; CLASSIFICATION RESULTS; CONVOLUTION NEURAL NETWORK; CONVOLUTIONAL NEURAL NETWORK; FEW-SHOT LEARNING; PROTOTYPE-BASED LEARNING; TRANSFER LEARNING; VISUAL OBJECT CLASSIFICATION;

DEEP NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CLASSIFICATION; CLASSIFIER; CONTROLLED STUDY; DEEP CONVOLUTION NEURAL NETWORK; FEW SHOT LEARNING; GLOBAL PROTOTYPE LEARNING; INFORMATION PROCESSING; LEARNING; MULTIFACTOR DIMENSIONALITY REDUCTION; PRIORITY JOURNAL; AUTOMATED PATTERN RECOGNITION; MACHINE LEARNING; PROCEDURES;

MACHINE LEARNING; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED;

EID: 85026747988     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2017.07.001     Document Type: Article

References (28)

1. Akata, Z., Malinowski, M., Fritz, M., & Schiele, B. (2016). Multi-Cue Zero-Shot Learning with Strong Supervision, arXiv preprint arXiv:1603.08754.
2. Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Return of the devil in the details: Delving deep into convolutional nets. In British machine vision conference.
3. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L., Imagenet: A large-scale hierarchical image database. IEEE conference on computer vision and pattern recognition, 2009, CVPR 2009, 2009, IEEE, 248–255.
4. de Vries, H., Memisevic, R., & Courville, A. (2016). Deep learning vector quantization. In European symposium on artificial neural networks, computational intelligence and machine learning.
5. Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., & Tzeng, E. et al. (2014). DeCAF: A deep convolutional activation feature for generic visual recognition. In ICML (pp. 647–655).
6. Fink, M., Object classification from a single example utilizing class relevance metrics. Advances in Neural Information Processing Systems 17 (2005), 449–456.
7. Fritzke, B., A growing neural gas network learns topologies. Advances in Neural Information Processing Systems 7 (1995), 625–632.
8. Hariharan, B., & Girshick, R. (2016). Low-shot visual object recognition, arXiv preprint arXiv:1606.02819.
9. Hecht, T., Gepperth, A., Computational advantages of deep prototype-based learning. International conference on artificial neural networks, 2016, Springer, 121–127.
10. Jetley, S., Romera-Paredes, B., Jayasumana, S., & Torr, P. (2015). Prototypical Priors: From Improving Classification to Zero-Shot Learning, arXiv preprint arXiv:1512.01192.
11. Krizhevsky, A., Sutskever, I., Hinton, G.E., Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, 1097–1105.
12. Lake, B.M., Salakhutdinov, R.R., Tenenbaum, J., One-shot learning by inverting a compositional causal process. Advances in neural information processing systems, 2013, 2526–2534.
13. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B., Human-level concept learning through probabilistic program induction. Science 350:6266 (2015), 1332–1338.
14. Lampert, C.H., Nickisch, H., Harmeling, S., Learning to detect unseen object classes by between-class attribute transfer. IEEE conference on computer vision and pattern recognition, 2009, CVPR 2009, 2009, IEEE, 951–958.
15. LeCun, Y., Bengio, Y., Hinton, G., Deep learning. Nature 521:7553 (2015), 436–444.
16. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition. Proceedings of the IEEE 86:11 (1998), 2278–2324.
17. Li, F.-F., Fergus, R., Perona, P., One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence 28:4 (2006), 594–611.
18. Maaten, L.v.d., Hinton, G., Visualizing data using t-SNE. Journal of Machine Learning Research (JMLR) 9:Nov (2008), 2579–2605.
19. Miller, G.A., WordNet: a lexical database for English. Communications of the ACM 38:11 (1995), 39–41.
20. Pan, S.J., Yang, Q., A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22:10 (2010), 1345–1359.
21. Rezende, D. J., Mohamed, S., Danihelka, I., Gregor, K., & Wierstra, D. (2016). One-Shot Generalization in Deep Generative Models, arXiv preprint arXiv:1603.05106.
22. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV) 115:3 (2015), 211–252, 10.1007/s11263-015-0816-y.
23. Sato, A., Yamada, K., Generalized learning vector quantization. Advances in Neural Information Processing Systems, 1996, 423–429.
24. Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 815–823).
25. Vedaldi, A., & Lenc, K. (2015). MatConvNet –convolutional neural networks for MATLAB. In Proceeding of the ACM int. conf. on multimedia.
26. Wang, Y., Cottrell, G.W., Bikers are like tobacco shops, formal dressers are like suits: recognizing urban tribes with caffe. 2015 IEEE winter conference on applications of computer vision, 2015, IEEE, 876–883.
27. Wang, Y.-X., Hebert, M., Learning to learn: model regression networks for easy small sample learning. European conference on computer vision, 2016, Springer, 616–634.
28. Zhang, Z., & Saligrama, V. (2015). Zero-shot learning via semantic similarity embedding. In Proceedings of the IEEE international conference on computer vision (pp. 4166–4174).