A pipeline combining SuperPoint, CLIPSeg, SAM, and a GCN achieves few-shot part segmentation on synthetic cranes and DAVIS 2017, but its reported numbers are undermined by test-set hyperparameter tuning.
Superpoint: Self-supervised interest point detection and description
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Few-shot Structure-Informed Machinery Part Segmentation with Foundation Models and Graph Neural Networks
A pipeline combining SuperPoint, CLIPSeg, SAM, and a GCN achieves few-shot part segmentation on synthetic cranes and DAVIS 2017, but its reported numbers are undermined by test-set hyperparameter tuning.