InstructPart is a new benchmark of 2,400 household images with part masks and task instructions, and current vision-language models score poorly on it while a fine-tuned LISA/DINOv2 baseline more than doubles accuracy.
Title resolution pending
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
-
InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
InstructPart is a new benchmark of 2,400 household images with part masks and task instructions, and current vision-language models score poorly on it while a fine-tuned LISA/DINOv2 baseline more than doubles accuracy.