INT improves task-generic promptable segmentation by progressively mining negative candidates, using VLM output differences after masking to select and refine instance-specific prompts.
Multi-weight partial domain adaptation
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
-
INT: Instance-Specific Negative Mining for Task-Generic Promptable Segmentation
INT improves task-generic promptable segmentation by progressively mining negative candidates, using VLM output differences after masking to select and refine instance-specific prompts.