Understanding Multi-Granularity for Open-Vocabulary Part Segmentation

Jiho Choi, Seonho Lee, Seungho Lee, Minhyun Lee, Hyunjung Shim

Keywords: part segmentation, open-vocabulary, multi-granularity

TL;DR: PartCLIPSeg is a novel framework that enhances open-vocabulary part segmentation by utilizing object-level contexts and attention control, significantly outperforming existing methods on major datasets.

Abstract:

Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies.
Our study highlights the inherent complexities of part segmentation due to intricate boundaries and diverse granularity, reflecting the knowledge-based nature of part identification.
To address these challenges, we propose PartCLIPSeg, a novel framework utilizing generalized parts and object-level contexts to mitigate the lack of generalization in fine-grained parts.
PartCLIPSeg integrates competitive part relationships and attention control, alleviating ambiguous boundaries and underrepresented parts.
Experimental results demonstrate that PartCLIPSeg outperforms existing state-of-the-art OVPS methods, offering refined segmentation and an advanced understanding of part relationships within images.
Through extensive experiments, our model demonstrated a significant improvement over the state-of-the-art models on the Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets.

Primary Area: Machine vision

Submission Number: 10487