Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation
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 …
has attracted much attention due to low annotation costs. Existing methods often rely on …
Tree energy loss: Towards sparsely annotated semantic segmentation
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 …
with coarse-grained (ie, point-, scribble-, and block-wise) supervisions, where only a small …
Sparsely annotated semantic segmentation with adaptive gaussian mixtures
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 …
images with sparse labels (ie, points or scribbles). Existing methods mainly focus on …
Weakly-supervised camouflaged object detection with scribble annotations
Existing camouflaged object detection (COD) methods rely heavily on large-scale datasets
with pixel-wise annotations. However, due to the ambiguous boundary, annotating …
with pixel-wise annotations. However, due to the ambiguous boundary, annotating …
[HTML][HTML] Large-scale road extraction from high-resolution remote sensing images based on a weakly-supervised structural and orientational consistency constraint …
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 …
large number of densely labeled road samples, limiting their potential in large-scale …
Scribformer: Transformer makes cnn work better for scribble-based medical image segmentation
Most recent scribble-supervised segmentation methods commonly adopt a CNN framework
with an encoder-decoder architecture. Despite its multiple benefits, this framework generally …
with an encoder-decoder architecture. Despite its multiple benefits, this framework generally …
SATS: Self-attention transfer for continual semantic segmentation
Continually learning to segment more and more types of image regions is a desired
capability for many intelligent systems. However, such continual semantic segmentation …
capability for many intelligent systems. However, such continual semantic segmentation …
Structure-aware weakly supervised network for building extraction from remote sensing images
H Chen, L Cheng, Q Zhuang, K Zhang… - … on Geoscience and …, 2022 - ieeexplore.ieee.org
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 …
images (RSIs) has shown excellent performance, which requires large amounts of training …
Blpseg: Balance the label preference in scribble-supervised semantic segmentation
Scribble-supervised semantic segmentation is an appealing weakly supervised technique
with low labeling cost. Existing approaches mainly consider diffusing the labeled region of …
with low labeling cost. Existing approaches mainly consider diffusing the labeled region of …
ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation
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 …
the development of autonomous navigation systems. However, annotating complex urban …