Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training
paradigm, successfully introduces text supervision to vision models. It has shown promising …

Replay is the reactivation of one or more neural patterns that are similar to the activation
patterns experienced during past waking experiences. Replay was first observed in …

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

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 learning empowers the mainstream medical image segmentation methods.
Nevertheless, current deep segmentation approaches are not capable of efficiently and …

Deep learning models are known to suffer from the problem of catastrophic forgetting when
they incrementally learn new classes. Continual learning for semantic segmentation (CSS) …

A fundamental and challenging problem in deep learning is catastrophic forgetting, ie, the
tendency of neural networks to fail to preserve the knowledge acquired from old tasks when …

The ability to dynamically extend a model to new data and classes is critical for multiple
organ and tumor segmentation. However, due to privacy regulations, accessing previous …

Despite the significant recent progress made on 3D point cloud semantic segmentation, the
current methods require training data for all classes at once, and are not suitable for real-life …