Dance

Statistics

Cartography

Literature

Set (abstract data type)

Computer science

Code (set theory)

Image segmentation

Segmentation

Pattern recognition (psychology)

Mathematics

Pipeline (software)

Politics

Geography

Political science

Object (grammar)

Artificial intelligence

Representation (politics)

Matching (statistics)

Programming language

Meteorology

Contour line

Computer vision

Contour-based instance segmentation methods are attractive due to their efficiency. However, existing contour-based methods either suffer from lossy representation, complex pipeline or difficulty in model training, resulting in sub-par mask accuracy on challenging datasets like MS-COCO. In this work, we propose a novel deep attentive contour model, named DANCE, to achieve better instance segmentation accuracy while remaining good efficiency. To this end, DANCE applies two new designs: attentive contour deformation to refine the quality of segmentation contours and segment-wise matching to ease the model training. Comprehensive experiments demonstrate DANCE excels at deforming the initial contour in a more natural and efficient way towards the real object boundaries. Effectiveness of DANCE is also validated on the COCO dataset, which achieves 38.1% mAP and outperforms all other contour-based instance segmentation models. To the best of our knowledge, DANCE is the first contour-based model that achieves comparable performance to pixel-wise segmentation models. Code is available at https://github.com/lkevinzc/dance.

DANCE : A Deep Attentive Contour Model for Efficient Instance Segmentation