Abstract Class-Incremental Learning (CIL) requires a learning system to continually learn
new classes without forgetting. Despite the strong performance of Pre-Trained Models …

Nowadays, real-world applications often face streaming data, which requires the learning
system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from
very few data (5 samples) without forgetting the previously learned classes. Recent works in …

Exemplar-free class-incremental learning using a backbone trained from scratch and
starting from a small first task presents a significant challenge for continual representation …

Abstract The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually
learn new knowledge while preventing forgetting of the old knowledge, without storing any …

In autonomous driving, even a meticulously trained model can encounter failures when
facing unfamiliar scenarios. One of these scenarios can be formulated as an online …

In this work, we study the problem of continual learning (CL) where the goal is to learn a
model on a sequence of tasks, under the assumption that the data from the previous tasks …

Class-incremental learning is a challenging problem, where the goal is to train a model that
can classify data from an increasing number of classes over time. With the advancement of …

Currently, most applications in the Industrial Internet of Things (IIoT) still rely on CNN-based
neural networks. Although Transformer-based large models (LMs), including language …