We tackle catastrophic forgetting problem in the context of class-incremental learning for
video recognition, which has not been explored actively despite the popularity of continual …

Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes
with very few labeled samples, without forgetting the knowledge of already learnt classes …

Traditional learning systems are trained in closed-world for a fixed number of classes, and
need pre-collected datasets in advance. However, new classes often emerge in real-world …

Conclusion 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 …

As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a
sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and …

Neural networks suffer from catastrophic forgetting when sequentially learning tasks phase-
by-phase, making them inapplicable in dynamically updated systems. Class-incremental …

Deep models have shown to be vulnerable to catastrophic forgetting, a phenomenon that
the recognition performance on old data degrades when a pre-trained model is fine-tuned …

Data-driven algorithms are studied and deployed in diverse domains to support critical
decisions, directly impacting people's well-being. As a result, a growing community of …

In contrast to the natural capabilities of humans to learn new tasks in a sequential fashion,
neural networks are known to suffer from catastrophic forgetting, where the model's …

In the real world, a desirable Visual Question Answering model is expected to provide
correct answers to new questions and images in a continual setting (recognized as CL …