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 …

Class incremental semantic segmentation aims to strike a balance between the model's
stability and plasticity by maintaining old knowledge while adapting to new concepts …

Large pre-trained transformers are on top of contemporary semantic segmentation
benchmarks, but come with high computational cost and a lengthy training. To lift this …

Existing class-incremental semantic segmentation (CISS) methods mainly tackle
catastrophic forgetting and background shift, but often overlook another crucial issue. In …

Instance segmentation requires labor-intensive manual labeling of the contours of complex
objects in images for training. The labels can also be provided incrementally in practice to …

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 …

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 …

Continual learning is an effective way to overcome catastrophic forgetting (CF) in
incremental learning for semantic segmentation. The existing continual semantic …

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