Extracting and using class-discriminative features is critical for
fine-...
Medical image segmentation methods normally perform poorly when there is...
The emergence of large models, also known as foundation models, has brou...
Continual Semantic Segmentation (CSS) extends static semantic segmentati...
Contemporary segmentation methods are usually based on deep fully
convol...
Large-scale training data with high-quality annotations is critical for
...
In this paper, we propose a 3D fully convolutional encoder-decoder
archi...
Existing semantic segmentation works mainly focus on learning the contex...
Recent works have achieved great success in improving the performance of...
Attention mechanisms are widely used in salient object detection models ...