1. Cluster2Former: Semisupervised Clustering Transformers for Video Instance Segmentation.
- Author
-
Fóthi, Áron, Szlatincsán, Adrián, and Somfai, Ellák
- Subjects
SUPERVISED learning ,PERFORMANCE standards ,VIDEOS ,VIDEO processing - 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]
- Published
- 2024
- Full Text
- View/download PDF