CMP combines LLM-generated semantic references, automatically composed SAM prompts, and frequency-domain alignment to set new state-of-the-art results on four cross-domain few-shot segmentation benchmarks.
Datasets and Evaluation Metrics We train our model on PASCAL VOC 2012 with SBD aug- mentation and evaluate across diverse target domains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation
CMP combines LLM-generated semantic references, automatically composed SAM prompts, and frequency-domain alignment to set new state-of-the-art results on four cross-domain few-shot segmentation benchmarks.