DPSeg adds Stable Diffusion generated visual prompts to CLIP text prompts to build cost volumes for open-vocabulary semantic segmentation, reporting state-of-the-art mIoU on five benchmarks.
Cdul: Clip-driven unsupervised learning for multi-label image classification
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
-
DPSeg: Dual-Prompt Cost Volume Learning for Open-Vocabulary Semantic Segmentation
DPSeg adds Stable Diffusion generated visual prompts to CLIP text prompts to build cost volumes for open-vocabulary semantic segmentation, reporting state-of-the-art mIoU on five benchmarks.