☆ 4.7 Article

Mask encoding: A general instance mask representation for object segmentation

PATTERN RECOGNITION (2022)

JSPNet: Learning joint semantic & instance segmentation of point clouds via feature self-similarity and cross-task probability

Feng Chen et al.

Summary: The paper introduces a novel method named JSPNet for simultaneous semantic and instance segmentation of 3D point cloud. By incorporating feature fusion and probability-based correlation modules, the method enhances feature distinctiveness and interrelation, demonstrating superior performance in experiments compared to existing approaches.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT Images

Xiaoming Liu et al.

Summary: This paper proposed a novel weakly supervised segmentation method for COVID-19 infections in CT slices, which only requires scribble supervision and is enhanced with the uncertainty-aware self-ensembling and transformation consistent techniques. Experimental results demonstrate that the proposed method is more effective than other weakly supervised methods and achieves similar performance as those fully supervised.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Single annotated pixel based weakly supervised semantic segmentation under driving scenes

Xi Li et al.

Summary: This study proposes a lightweight labeling process for weakly supervised semantic segmentation tasks under complex driving scenes by providing a single annotated pixel for each category. A three-step process is built for pseudo labels generation, which progressively implements feature representation, image inference, and context-location based refinement, achieving efficient completion of the semantic segmentation task.

PATTERN RECOGNITION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence