Iemask r-cnn: Information-enhanced mask r-cnn
The instance segmentation task is relatively difficult in computer vision, which requires not
only high-quality masks but also high-accuracy instance category classification. Mask R …
only high-quality masks but also high-accuracy instance category classification. Mask R …
Transformer-based efficient salient instance segmentation networks with orientative query
Salient instance segmentation (SIS) can be considered as the next generation task for the
saliency detection community. Most of the existing state-of-the-art methods used for this …
saliency detection community. Most of the existing state-of-the-art methods used for this …
KepSalinst: Using peripheral points to delineate salient instances
Salient instance segmentation (SIS) is an emerging field that evolves from salient object
detection (SOD), aiming at identifying individual salient instances using segmentation maps …
detection (SOD), aiming at identifying individual salient instances using segmentation maps …
Unsupervised Salient Instance Detection
The significant amount of manual efforts in annotating pixel-level labels has triggered the
advancement of unsupervised saliency learning. However without supervision signals state …
advancement of unsupervised saliency learning. However without supervision signals state …
Borderpointsmask: One-stage instance segmentation with boundary points representation
The mechanism of human vision can easily detect and segment objects based on boundary
information. Even though the deep learning instance segmentation model based on …
information. Even though the deep learning instance segmentation model based on …
SCG: Saliency and contour guided salient instance segmentation
Different from conventional instance segmentation, salient instance segmentation (SIS)
faces two difficulties. The first is that it involves segmenting salient instances only while …
faces two difficulties. The first is that it involves segmenting salient instances only while …
Instance-level context attention network for instance segmentation
Instance segmentation has made great progress in recent years. However, current
mainstream detection-based methods ignore the process of distinguishing different …
mainstream detection-based methods ignore the process of distinguishing different …
Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation
Segment Anything Model (SAM) has demonstrated powerful zero-shot segmentation
performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) …
performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) …