Fetching the paper…

Reading the bibliography…

2021

PyCIL: A Python Toolbox for Class-Incremental Learning

Zhou, Da-Wei, Wang, Fu-Yun, Ye, Han-Jia et al.

Original
PDF
Post on X

Understand

Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process.

However, real-world applications often face the incoming new classes, and a model should incorporate them continually.
The learning paradigm is called Class-Incremental Learning (CIL).
We propose a Python toolbox that implements several key algorithms for class-incremental learning to ease the burden of researchers in the machine learning community.

PyCIL: A Python Toolbox for Class-Incremental Learning · Around

Built on

Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al · 2017
Earlier work this paper cites.
Learning without forgetting
Zhizhong Li and Derek Hoiem · 2017
Earlier work this paper cites.
icarl: Incremental classifier and representation learning
Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert · 2017
Earlier work this paper cites.

Similar

Gradient episodic memory for continual learning
David Lopez-Paz and Marc’Aurelio Ranzato · 2017
Cited alongside, same era.
Large scale incremental learning
Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu · 2019
Cited alongside, same era.
Maintaining discrimination and fairness in class incremental learning
Bowen Zhao, Xi Xiao, Guojun Gan, Bin Zhang, and Shu-Tao Xia · 2020
Cited alongside, same era.

Then

Podnet: Pooled outputs distillation for small-tasks incremental learning
Arthur Douillard, Matthieu Cord, Charles Ollion, Thomas Robert, and Eduardo Valle · 2020
Later among the works it cites.
Der: Dynamically expandable representation for class incremental learning
Shipeng Yan, Jiangwei Xie, and Xuming He · 2021
Closest in time.
Co-transport for class-incremental learning
Da-Wei Zhou, Han-Jia Ye, and De-Chuan Zhan · 2021
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…