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 …

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 …

In this paper, we introduce audio-visual class-incremental learning, a class-incremental
learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual …

Deep Learning models have achieved remarkable performance in tasks such as image
classification or generation, often surpassing human accuracy. However, they can struggle …

Continual learning algorithms which keep the parameters of new tasks close to that of
previous tasks, are popular in preventing catastrophic forgetting in sequential task learning …

Incremental semantic segmentation focuses on continually learning the segmentation of
new coming classes without obtaining the training data from previously seen classes …

Deep learning models have achieved remarkable success in multi-type nuclei
segmentation. These models are mostly trained at once with the full annotation of all types of …

Continual learning, also known as incremental learning or life-long learning, stands at the
forefront of deep learning and AI systems. It breaks through the obstacle of one-way training …

The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation
task by incrementally learning newly added classes. Previous work has introduced …

In this study, we focus on Continual Semantic Segmentation (CSS) and present a novel
approach to tackle the issue of existing methods struggling to learn new classes. The …