SOURCE-LINKED INTELLIGENCE

PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Prompt learning efficiently adapts vision-language models (VLMs) to downstream tasks, but gains on seen classes often come at the expense of generalization to unseen classes. To address this limitation, we propose prompt ensembling with training-free routing (PETR), whose key innovation is a carefully designed dual-prompt architecture: two complementary prompts are learned from different data and objectives to emphasize seen class discrimination and unseen-class generalization, respectively. During training, both prompts are fine-tuned using a shared frozen CLIP backbone, and statistical infor

Read original source ↗ Open in workspace

recordType

paper

region

Global