IEEE Robotics & Automation Magazine - June 2020 - 16

11215618. The authors would like to
thank Hong Pong Ho from the Intel
RealSense Team for the technical support
of RealSense cameras for recording the
high-quality RGB-D data sequences. The
author list is in alphabetical order:
R.H.M. Chan, F. Feng, X. Hao, C. Lan,
Q. Liu, V. Lomonaco, G.I. Parisi, Q. She,
and Q. Yang prepared the report. The
other co-authors were competition final-
ists. The corresponding author is Qi She
(qi.she@intel.com).
References
[1] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and
L. Fei-Fei, "Imagenet: A large-scale hierarchical
image database," in Proc. IEEE Conf. Computer
Vision and Pattern Recognition (CVPR), 2009, pp.
248-255. doi: 10.1109/CVPR.2009.5206848.
[2] T.-Y. Lin et al., "Microsoft COCO: Common
objects in context," in Proc. European Conf. Computer Vision (ECCV), 2014, pp. 740-755.
[3] F. Feng, R. H. M. Chan, X. Shi, Y. Zhang, and
Q. She, "Challenges in task incremental learning
for assistive robotics," IEEE Access, vol. 8, pp.
3434-3441, Nov. 25, 2019. doi: 10.1109/ACCESS.
2019.2955480.
[4] Q. She and A. Wu, "Neural dynamics discovery
via Gaussian process recurrent neural networks,"
in Proc 35th Conf. Uncertainty Artificial Intelligence (UAI), 2019, p. 159.
[5] Q. She, and R.H.M. Chan, "Stochastic dynami-
cal systems based latent structure discovery in
high-dimensional time series," in Proc. 2018 IEEE
Int. Conf. Acoustics, Speech and Signal Processing
(ICASSP), 2018, pp. 886-890. doi: 10.1109/
ICASSP.2018.8461755.

IMAGE LICENSED BY GRAPHIC STOCK

16

*

[6] Q. She, Y. Gao, X. Kai, and R. H. M. Chan,
"Reduced-rank linear dynamical systems," in Proc.
32nd AAAI Conf. Artificial Intelligence (AAAI),
2018, pp. 4050-4057.
[7] Z. Li and D. Hoiem, "Learning without forget-
ting," IEEE Trans. Pattern Anal. Mach. Intell., vol.
40, no. 12, pp. 2935-2947, 2017. doi: 10.1109/
TPAMI.2017.2773081.
[8] J. Kirkpatrick et al., "Overcoming catastrophic
forgetting in neural networks," Proc. Natl. Acad.
Sci. (PNAS), vol. 114, no. 13, pp. 3521-3526, 2017.
doi: 10.1073/pnas.1611835114.
[9] F. Zenke, B. Poole, and S. Ganguli, "Continual
learning through synaptic intelligence," in Proc.
34th Int. Conf. Machine Learning (ICML), 2017, pp.
3987-3995.
[10] N. Y. Masse, G. D. Grant, and D. J. Freedman,
"Alleviating catastrophic forgetting using con-
text-dependent gating and synaptic stabilization,"
Proc. Nat. Academy Sci. (PNAS), vol. 115, no. 44,
pp. 467-475, 2018. doi: 10.1073/pnas.1803839115.
[11] J. Yoon, E. Yang, J. Lee, and S. J. Hwang, Life-
long learning with dynamically expandable net-
works. 2017. [Online]. Available: arXiv:1708.01547
[12] Z. Wang, Q. She, and T. E. Ward, Generative
adversarial networks: A survey and taxonomy.
2019. [Online]. Available: arXiv:1906.01529
[13] Z. Wang, Q. She, A. F. Smeaton, T. E. Ward,
and G. Healy, A Neuro-AI interface for evaluating
generative adversarial networks. 2020. [Online].
Available: arXiv:2003.03193
[14] Z. Wang, Q. She, A. F. Smeaton, T. E. Ward,
and G. Healy, Neuroscore: A brain-inspired evalu-
ation metric for generative adversarial networks.
2019. [Online]. Available: arXiv: 1905.04243
[15] S.-A. Rebuffi, A. Kolesnikov, G. Sperl, and C.
H. Lampert, "iCaRL: Incremental classifier and

We want
to hear
from you!

IEEE ROBOTICS & AUTOMATION MAGAZINE

*

JUNE 2020

representation learning," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017,
pp. 2001-2010.
[16] H. Shin, J. K. Lee, J. Kim, and J. Kim,
"Cont i nua l lea rni ng w it h deep generat ive
replay," in Proc. Advances Neural Information
Processing Systems (NIPS), 2017, pp. 2990-
2999.
[17] N. Kamra, U. Gupta, and Y. Liu, Deep genera-
tive dual memory network for continual learning.
2017. [Online]. Available: arXiv:1710.10368
[18] G. M. van de Ven and A. S. Tolias, Generative
replay with feedback connections as a general
strategy for continual learning. 2018. [Online].
Available: arXiv:1809.10635
[19] Q. She et al., "IROS 2019 Lifelong Robotic
Vision Challenge-Lifelong object recognition
report," Nov. 2019. Accessed on: Apr. 2020.
[Online]. Available: ht tps://ar x iv.org /abs/
2004.14774
[20] Q. She, "OpenLORIS-object dataset and
Benchmark," Nov. 2019. Accessed on: Apr. 2020.
[Online]. Available: https://lifelong-robotic-vision
.github.io/dataset/Data_Object-Recognition
[21] Q. She et a l., Open LOR IS - Objec t: A
robotic vision dataset and benchmark for life-
long deep learning. 2020. [Online]. Available:
arXiv:1911.06487v2
[22] L. Pellegrini, G. Graffieti, V. Lomonaco,
and D. Maltoni, Latent replay for real-time
continual learning. 2019. [Online]. Available:
arXiv:1912.01100v2
[23] W. Liu et al., "SSD: Single shot multibox
detector," in Proc. European Conf. Computer Vision
(ECCV), 2016, pp. 21-37. doi: 10.1007/978-3-31946448-0_2.



Do you like what you're reading?
Your feedback is important.
Let us know-send the editor-in-chief an e-mail!
https://lifelong-robotic-vision.github.io/dataset/Data_Object-Recognition https://lifelong-robotic-vision.github.io/dataset/Data_Object-Recognition
IEEE Robotics & Automation Magazine - June 2020

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - June 2020
