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

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 …

Explaining node predictions in graph neural networks (GNNs) often boils down to finding
graph substructures that preserve predictions. Finding these structures usually implies back …

Abstract Class-Incremental Learning (CIL) trains a model to continually recognize new
classes from non-stationary data while retaining learned knowledge. A major challenge of …

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

Abstract Class Incremental Semantic Segmentation (CISS), within Incremental Learning for
semantic segmentation, targets segmenting new categories while reducing the catastrophic …

This study explores the emerging area of continual panoptic segmentation, highlighting
three key balances. First, we introduce past-class backtrace distillation to balance the …

Continual learning (CL) breaks off the one-way training manner and enables a model to
adapt to new data, semantics and tasks continuously. However, current CL methods mainly …

Despite significant progress made in image semantic segmentation, most research has
primarily focused on daytime scenes. Semantic segmentation of nighttime images is equally …

Class incremental semantic segmentation aims to preserve old knowledge while learning
new tasks, however, it is impeded by catastrophic forgetting and background shift issues …