To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

Continual learning (CL) is a particular machine learning paradigm where the data
distribution and learning objective change through time, or where all the training data and …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

For future learning systems, incremental learning is desirable because it allows for: efficient
resource usage by eliminating the need to retrain from scratch at the arrival of new data; …

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 …

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks
such as semantic segmentation, requiring large datasets and substantial computational …

In this work, we study the continual semantic segmentation problem, where the deep neural
networks are required to incorporate new classes continually without catastrophic forgetting …

Despite their effectiveness in a wide range of tasks, deep architectures suffer from some
important limitations. In particular, they are vulnerable to catastrophic forgetting, ie they …

Deep networks allow to obtain outstanding results in semantic segmentation, however they
need to be trained in a single shot with a large amount of data. Continual learning settings …

Federated learning-based semantic segmentation (FSS) has drawn widespread attention
via decentralized training on local clients. However, most FSS models assume categories …