Back to Search
Start Over
Panoptic Segmentation with Convex Object Representation.
- Source :
-
Computer Journal . Jun2024, Vol. 67 Issue 6, p2009-2019. 11p. - Publication Year :
- 2024
-
Abstract
- The accurate representation of objects holds pivotal significance in the realm of panoptic segmentation. Presently, prevalent object representation methodologies, including box-based, keypoint-based and query-based techniques, encounter a challenge known as the 'representation confusion' issue in specific scenarios, often resulting in the mislabeling of instances. In response, this paper introduces Convex Object Representation (COR), a straightforward yet highly effective approach to address this problem. COR leverages a CNN-based Euclidean Distance Transform to convert the target instance into a convex heatmap. Simultaneously, it offers a parallel embedding method for encoding the object. Subsequently, COR characterizes objects based on the distinctive embedding vectors of their convex vertices. This paper seamlessly integrates COR into a state-of-the-art query-based panoptic segmentation framework. Experimental findings validate that COR successfully mitigates the representation confusion predicament, enhancing segmentation accuracy. The COR-augmented methods exhibit notable improvements of +1.3 and +0.7 points in PQ on the Cityscapes validation and MS COCO panoptic 2017 validation datasets, respectively. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 00104620
- Volume :
- 67
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- Computer Journal
- Publication Type :
- Academic Journal
- Accession number :
- 178338251
- Full Text :
- https://doi.org/10.1093/comjnl/bxad119