Skip to main content

🏢 Graduate School of Artificial Intelligence, KAIST

Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
·2683 words·13 mins· loading · loading
Computer Vision Image Segmentation 🏢 Graduate School of Artificial Intelligence, KAIST
PartCLIPSeg, a novel framework, leverages generalized parts and object-level contexts to achieve significant improvements in open-vocabulary part segmentation, outperforming state-of-the-art methods.