BROWSE
Detail
Conference Paper
Object-centric Scene Representation Learning via SAM
Cited 0 time in 
Share 
Share
- Authors
- Donghun Lee, Samyeul Noh, Ingook Jang, Seonghyun Kim, Soonyoung Song, Heechul Bae
- Issue Date
- 2024-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2024, pp.215-217
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Recent advancements in the segmentation foundation model SAM have demonstrated exceptional performance in image segmentation. This study introduces object-centric representation learning, capitalizing on the segmentation outcomes derived from the foundational segmentation model SAM to elevate generalization performance and accelerate training within scene representation learning. Our approach involves a simple yet effective method to fine-tune unsupervised feature extraction in object-centric learning for scene representation. We conduct an effort to enhance the performance of unsupervised representation learning in out-of-distribution situations, resulting in improved performance in single-object out-of-distribution (OOD) scenarios.
- KSP Keywords
- Generalization performance, Improved performance, Object-centric, Representation learning, Scene Representation, image segmentation, unsupervised feature extraction