PyCIL: A Python Toolbox for Class-Incremental Learning
This provides a practical tool for researchers in machine learning to ease the burden of implementing CIL algorithms, but it is incremental as it focuses on software development rather than novel algorithmic contributions.
The authors tackled the problem of class-incremental learning (CIL) by developing PyCIL, a Python toolbox that implements key algorithms, including foundational works like EWC and iCaRL, as well as state-of-the-art methods, to facilitate research in this area.
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. The toolbox contains implementations of a number of founding works of CIL such as EWC and iCaRL, but also provides current state-of-the-art algorithms that can be used for conducting novel fundamental research. This toolbox, named PyCIL for Python Class-Incremental Learning, is available at https://github.com/G-U-N/PyCIL