Towards lifelong object recognition: A dataset and benchmark

Li, 2020, A baseline regularization scheme for transfer learning with convolutional neural networks, Pattern Recognit., 98, 107049, 10.1016/j.patcog.2019.107049 Lopez-Paz, 2017, Gradient episodic memory for continual learning, 6467 Mohassel, 2017, SecureML: a system for scalable privacy-preserving machine learning, 19 Zhou, 2020, Two-stage knowledge transfer framework for image classification, Pattern Recognit., 107, 107529, 10.1016/j.patcog.2020.107529 Khamassi, 2018, Discussion and review on evolving data streams and concept drift adapting, Evolving Syst., 9, 1, 10.1007/s12530-016-9168-2 Kirkpatrick, 2017, Overcoming catastrophic forgetting in neural networks, Proc. Natl. Acad. Sci.(PNAS), 3521, 10.1073/pnas.1611835114 Schwarz, 2018, Progress & compress: a scalable framework for continual learning, 4535 Sünderhauf, 2018, The limits and potentials of deep learning for robotics, Int. J. Rob. Res., 37, 405, 10.1177/0278364918770733 Maltoni, 2016, Semi-supervised tuning from temporal coherence, 2509 She, 2020, OpenLORIS-object: a robotic vision dataset and benchmark for lifelong deep learning, 4767 G.M. Van de Ven, A.S. Tolias, Three scenarios for continual learning, arXiv preprint arXiv:1904.07734(2019). Mermillod, 2013, The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects, Front. Psychol., 4, 504, 10.3389/fpsyg.2013.00504 Li, 2017, Learning without forgetting, IEEE Trans. Pattern Anal. Mach.Intell., 40, 2935, 10.1109/TPAMI.2017.2773081 Zenke, 2017, Continual learning through synaptic intelligence, vol. 70, 3987 Masse, 2018, Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization, Proc. Natl. Acad. Sci. (PNAS), 115, 467, 10.1073/pnas.1803839115 Yoon, 2018, Lifelong learning with dynamically expandable network Rebuffi, 2017, iCaRL: incremental classifier and representation learning, 2001 Shin, 2017, Continual learning with deep generative replay, 2990 Y. Wu, Y. Chen, L. Wang, Y. Ye, Z. Liu, Y. Guo, Z. Zhang, Y. Fu, Incremental classifier learning with generative adversarial networks, arXiv preprint arXiv:1802.00853(2018). G.M. van de Ven, A.S. Tolias, Generative replay with feedback connections as a general strategy for continual learning, arXiv preprint arXiv:1809.10635(2018). Lao, 2021, FoCL: Feature-oriented continual learning for generative models, Pattern Recognit., 120, 108127, 10.1016/j.patcog.2021.108127 Maltoni, 2019, Continuous learning in single-incremental-task scenarios, Neural Netw., 116, 56, 10.1016/j.neunet.2019.03.010 Pellegrini, 2020, Latent replay for real-time continual learning, 10203 LeCun, 1998, Gradient-based learning applied to document recognition, Proc. IEEE, 86, 2278, 10.1109/5.726791 P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, P. Perona, Caltech-UCSD birds 200 (2010). Lai, 2011, A large-scale hierarchical multi-view RGB-D object dataset, 1817 Loghmani, 2018, Recognizing objects in-the-wild: where do we stand?, 2170 Lomonaco, 2017, CORe50: a new dataset and benchmark for continuous object recognition, 17 Wang, 2019, Fast online object tracking and segmentation: a unifying approach Parisi, 2019, Continual lifelong learning with neural networks: a review, Neural Netw., 10.1016/j.neunet.2019.01.012 He, 2021, Towards non-IID image classification: a dataset and baselines, Pattern Recognit., 110, 107383, 10.1016/j.patcog.2020.107383 Díaz-Rodríguez, 2018, Don’t forget, there is more than forgetting: new metrics for continual learning Khan, 2021, Transformers in vision: a survey, ACM Comput. Surv. (CSUR) Kim, 2021, ViLT: vision-and-language transformer without convolution or region supervision, 5583 S.A. Nene, S.K. Nayar, H. Murase, et al., Columbia object image library (coil-20)(1996). LeCun, 2004, Learning methods for generic object recognition with invariance to pose and lighting, 97 Nilsback, 2008, Automated flower classification over a large number of classes, 722 Krizhevsky, 2009, Learning Multiple Layers of Features from Tiny Images Wah, 2011, The Caltech-UCSD Birds-200-2011 Dataset