PyCIL: a Python toolbox for class-incremental learning

By Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, De-chuan Zhan. 2021

145 citations recorded by the source corpus.

We have presented PyCIL, a classincremental learning toolbox written in Python. It contains implementations of a number of founding studies of CIL, but also provides current state-of-the-art algorithms that can be used to conduct novel fundamental research. Code consistency makes it an easy tool for research purposes, teaching, and industrial applications.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, General Health Professions, Meta & Continual Learning, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In General Health Professions

In Meta & Continual Learning

In ML Systems & Hardware

Citations in the corpus

S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning (2022, methodology): “We implement EWC [32] and LwF [40] with pre-trained ViT-B/16 using the PyCIL toolbox [75].”
FOSTER: Feature Boosting and Compression for Class-Incremental Learning (2022, methodology): “Our method and all compared methods are implemented with Pytorch [33] and PyCIL [49].”
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, background): “Class-Incremental Learning is now a popular topic in the machine learning field [27], [28], [29], [30], [31], which can be roughly divided into two groups by whether saving exemplars of old class instances.”
Forward Compatible Few-Shot Class-Incremental Learning (2022, background): “Class-Incremental Learning (CIL): aims to learn from a sequence of new classes without forgetting old ones, which is now widely discussed in various computer vision tasks [13, 51, 62, 64].”
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning (2024, methodology): “In the experiments, we reimplement the above methods based on their source code and PyCIL [76].”
Deep Class-Incremental Learning: A Survey (2023, methodology): “Training details: We implement the above methods with PyTorch [198] and PyCIL [199].”
Divide and not forget: Ensemble of selectively trained experts in Continual Learning (2024, methodology): “We reproduce results using FACIL(Masana et al., 2022), and PyCIL(Zhou et al., 2021) benchmarks for this setting.”
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning (2022, background): “There are other methods that do not fall into these two groups [24, 29, 23, 46, 61, 66], and we refer the readers to [10, 36, 62] for a holistic review.”
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning (2024, methodology): “We use the PyCIL framework [53] as a basis for all our experiments.”
Class-Incremental Learning: A Survey (2023, methodology): “Training details: We implement the above methods with Py-Torch [210] and PyCIL [211].”