Back to Search
Start Over
Cluster2Former: Semisupervised Clustering Transformers for Video Instance Segmentation.
- Source :
-
Sensors (14248220) . Feb2024, Vol. 24 Issue 3, p997. 17p. - Publication Year :
- 2024
-
Abstract
- A novel approach for video instance segmentation is presented using semisupervised learning. Our Cluster2Former model leverages scribble-based annotations for training, significantly reducing the need for comprehensive pixel-level masks. We augment a video instance segmenter, for example, the Mask2Former architecture, with similarity-based constraint loss to handle partial annotations efficiently. We demonstrate that despite using lightweight annotations (using only 0.5% of the annotated pixels), Cluster2Former achieves competitive performance on standard benchmarks. The approach offers a cost-effective and computationally efficient solution for video instance segmentation, especially in scenarios with limited annotation resources. [ABSTRACT FROM AUTHOR]
- Subjects :
- *SUPERVISED learning
*PERFORMANCE standards
*VIDEOS
*VIDEO processing
Subjects
Details
- Language :
- English
- ISSN :
- 14248220
- Volume :
- 24
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- Sensors (14248220)
- Publication Type :
- Academic Journal
- Accession number :
- 175390699
- Full Text :
- https://doi.org/10.3390/s24030997