UPRE improves zero-shot domain adaptation for object detection by jointly learning text prompts and patch-level style-enhanced visual representations, reporting gains across nine benchmarks.
Diprompt: Disentan- gled prompt tuning for multiple latent domain generalization in federated learning
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
-
UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement
UPRE improves zero-shot domain adaptation for object detection by jointly learning text prompts and patch-level style-enhanced visual representations, reporting gains across nine benchmarks.