Abstract Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels
has attracted much attention due to low annotation costs. Existing methods often rely on …

Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network
with coarse-grained (ie, point-, scribble-, and block-wise) supervisions, where only a small …

Sparsely annotated semantic segmentation (SASS) aims to learn a segmentation model by
images with sparse labels (ie, points or scribbles). Existing methods mainly focus on …

Existing camouflaged object detection (COD) methods rely heavily on large-scale datasets
with pixel-wise annotations. However, due to the ambiguous boundary, annotating …

Fully supervised road segmentation neural networks from remote sensing images rely on a
large number of densely labeled road samples, limiting their potential in large-scale …

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework
with an encoder-decoder architecture. Despite its multiple benefits, this framework generally …

Continually learning to segment more and more types of image regions is a desired
capability for many intelligent systems. However, such continual semantic segmentation …

The use of fully supervised deep learning methods to extract buildings from remote sensing
images (RSIs) has shown excellent performance, which requires large amounts of training …

Scribble-supervised semantic segmentation is an appealing weakly supervised technique
with low labeling cost. Existing approaches mainly consider diffusing the labeled region of …

Annotation is a crucial first step in the semantic segmentation of urban images that facilitates
the development of autonomous navigation systems. However, annotating complex urban …