2019

Deep CNN-based Multi-task Learning for Open-Set Recognition

Oza, Poojan, Patel, Vishal M.

Understand

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition.

We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task learning framework.
We show that this approach results in better open-set recognition accuracy.
In our approach, reconstruction errors from the decoder network are utilized for open-set rejection.

Built on

The Annals of probability pp. 792–804 (1974)
Balkema, A.A., De Haan, L.: Residual life time at great age · 1974
Earlier work this paper cites.
the Annals of Statistics 3
Pickands III, J., et al.: Statistical inference using extreme order statistics · 1975
Earlier work this paper cites.
Technometrics 35
Grimshaw, S.D.: Computing maximum likelihood estimates for the generalized pareto distribution · 1993
Earlier work this paper cites.
Nene, S.A., Nayar, S.K., Murase, H., et al.: Columbia object image library (coil-20) (1996)
1996
Earlier work this paper cites.
Machine learning 28
Caruana, R.: Multitask learning · 1997
Earlier work this paper cites.
Journal of Machine Learning Research 9
Bartlett, P.L., Wegkamp, M.H.: Classification with a reject option using a hinge loss · 2008
Earlier work this paper cites.
In: Biometric Technology for Human Identification V, vol. 6944, p. 69440O. International Society for Optics and Photonics (2008)
Shi, Z., Kiefer, F., Schneider, J., Govindaraju, V.: Modeling biometric systems using the general pareto distribution (gpd) · 2008
Earlier work this paper cites.
Tech. rep., Citeseer (2009)
Krizhevsky, A.: Learning multiple layers of features from tiny images · 2009
Earlier work this paper cites.
AT&T Labs [Online]. Available: http://yann. lecun. com/exdb/mnist 2
LeCun, Y., Cortes, C., Burges, C.: Mnist handwritten digit database · 2010
Earlier work this paper cites.
In: Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pp. 3384–3391. IEEE (2010)
Perronnin, F., Liu, Y., Sánchez, J., Poirier, H.: Large-scale image retrieval with compressed fisher vectors · 2010
Earlier work this paper cites.
Journal of Machine Learning Research 11
Yuan, M., Wegkamp, M.: Classification methods with reject option based on convex risk minimization · 2010
Earlier work this paper cites.
In: NIPS workshop on deep learning and unsupervised feature learning, vol. 2011, p. 5 (2011)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning · 2011
Earlier work this paper cites.
IEEE transactions on pattern analysis and machine intelligence 33
Scheirer, W.J., Rocha, A., Micheals, R.J., Boult, T.E.: Meta-recognition: The theory and practice of recognition score analysis · 2011
Earlier work this paper cites.
In: Advances in neural information processing systems, pp. 1097–1105 (2012)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks · 2012
Earlier work this paper cites.
In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2472–2479 (2013)
Fragoso, V., Sen, P., Rodriguez, S., Turk, M.: Evsac: accelerating hypotheses generation by modeling matching scores with extreme value theory · 2013
Earlier work this paper cites.
IEEE transactions on pattern analysis and machine intelligence 35
Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition · 2013
Earlier work this paper cites.
arXiv preprint arXiv:1312.6199 (2013)
Original
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks · 2013
Earlier work this paper cites.
In: Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)
Da, Q., Yu, Y., Zhou, Z.H.: Learning with augmented class by exploiting unlabeled data · 2014
Earlier work this paper cites.
In: Advances in neural information processing systems, pp. 2672–2680 (2014)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets · 2014
Earlier work this paper cites.
In: European Conference on Computer Vision, pp. 393–409. Springer (2014)
Jain, L.P., Scheirer, W.J., Boult, T.E.: Multi-class open set recognition using probability of inclusion · 2014
Earlier work this paper cites.

Similar

online: http://www. cs. toronto. edu/kriz/cifar. html (2014)
Krizhevsky, A., Nair, V., Hinton, G.: The cifar-10 dataset · 2014
Cited alongside, same era.
IEEE transactions on pattern analysis and machine intelligence 36
Scheirer, W.J., Jain, L.P., Boult, T.E.: Probability models for open set recognition · 2014
Cited alongside, same era.
arXiv preprint arXiv:1409.1556 (2014)
Original
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition · 2014
Cited alongside, same era.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1893–1902 (2015)
Bendale, A., Boult, T.: Towards open world recognition · 2015
Cited alongside, same era.
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2015)
2015
Cited alongside, same era.
CS 231N (2015)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge · 2015
Cited alongside, same era.
International Journal of Computer Vision 115
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge · 2015
Cited alongside, same era.
In: Advances in Independent Component Analysis and Learning Machines, pp. 143–171. Elsevier (2015)
Valpola, H.: From neural pca to deep unsupervised learning · 2015
Cited alongside, same era.
In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1511–1519 (2015)
Xia, Y., Cao, X., Wen, F., Hua, G., Sun, J.: Learning discriminative reconstructions for unsupervised outlier removal · 2015
Cited alongside, same era.
arXiv preprint arXiv:1506.03365 (2015)
Original
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop · 2015
Cited alongside, same era.
arXiv preprint arXiv:1606.06565 (2016)
Original
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in ai safety · 2016
Cited alongside, same era.
In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1563–1572 (2016)
Bendale, A., Boult, T.E.: Towards open set deep networks · 2016
Cited alongside, same era.

Then

arXiv preprint arXiv:1709.01507 (2017)
Original
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks · 2017
Later among the works it cites.
In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269. IEEE (2017)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks · 2017
Later among the works it cites.
Machine Learning 106
Júnior, P.R.M., de Souza, R.M., Werneck, R.d.O., Stein, B.V., Pazinato, D.V., de Almeida, W.R., Penatti, O.A., Torres, R.d.S., Rocha, A.: Nearest neighbors distance ratio open-set classifier · 2017
Later among the works it cites.
arXiv preprint arXiv:1711.09325 (2017)
Original
Lee, K., Lee, H., Lee, K., Shin, J.: Training confidence-calibrated classifiers for detecting out-of-distribution samples · 2017
Later among the works it cites.
arXiv preprint arXiv:1706.02690 (2017)
Original
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks · 2017
Later among the works it cites.
Synthesis Lectures on Computer Vision 7
Scheirer, W.J.: Extreme value theory-based methods for visual recognition · 2017
Later among the works it cites.
arXiv preprint arXiv:1709.08716 (2017)
Original
Shu, L., Xu, H., Liu, B.: Doc: Deep open classification of text documents · 2017
Later among the works it cites.
In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–10 (2017)
You, C., Robinson, D.P., Vidal, R.: Provable selfrepresentation based outlier detection in a union of subspaces · 2017
Later among the works it cites.
arXiv preprint arXiv:1712.07107 (2017)
Original
Yuan, X., He, P., Zhu, Q., Bhat, R.R., Li, X.: Adversarial examples: Attacks and defenses for deep learning · 2017
Later among the works it cites.
IEEE transactions on pattern analysis and machine intelligence 39
Zhang, H., Patel, V.M.: Sparse representation-based open set recognition · 2017
Later among the works it cites.
arXiv preprint arXiv:1807.01653 (2018)
Original
Abati, D., Porrello, A., Calderara, S., Cucchiara, R.: And: Autoregressive novelty detectors · 2018
Later among the works it cites.
arXiv preprint arXiv:1805.10917 (2018)
Original
Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations · 2018
Later among the works it cites.
arXiv preprint arXiv:1812.04606 (2018)
Original
Hendrycks, D., Mazeika, M., Dietterich, T.G.: Deep anomaly detection with outlier exposure · 2018
Later among the works it cites.
arXiv preprint arXiv:1808.00529 (2018)
Original
Liu, S., Garrepalli, R., Dietterich, T.G., Fern, A., Hendrycks, D.: Open category detection with pac guarantees · 2018
Later among the works it cites.
In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 613–628 (2018)
Neal, L., Olson, M., Fern, X., Wong, W.K., Li, F.: Open set learning with counterfactual images · 2018
Later among the works it cites.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7689–7698 (2018)
Niu, L., Tang, Q., Veeraraghavan, A., Sabharwal, A.: Learning from noisy web data with category-level supervision · 2018
Later among the works it cites.
arXiv preprint arXiv:1801.05365 (2018)
Original
Perera, P., Patel, V.M.: Learning deep features for one-class classification · 2018
Later among the works it cites.
IEEE transactions on pattern analysis and machine intelligence 40
Rudd, E.M., Jain, L.P., Scheirer, W.J., Boult, T.E.: The extreme value machine · 2018
Later among the works it cites.
arXiv preprint arXiv:1812.04246 (2018)
Original
Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition · 2018
Later among the works it cites.

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…