DAT adapts vision-language models for open-vocabulary detection via self-supervised pseudo-labeling from closed-set detectors, improving performance on novel and known classes while fine-tuning under 0.8M parameters.
Learning transferable visual models from natural language supervision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Detector Teaches Itself: Lightweight Self-Supervised Adaptation for Open-Vocabulary Object Detection
DAT adapts vision-language models for open-vocabulary detection via self-supervised pseudo-labeling from closed-set detectors, improving performance on novel and known classes while fine-tuning under 0.8M parameters.