SOURCE-LINKED INTELLIGENCE

OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but often rely on increasingly complex designs such as heavy cross-modal fusion, staged training, and iterative annotation pipelines. We revisit whether such complexity is necessary in the era of stronger foundation models. Our finding is that unified OVD can be made substantially simpler with semantic-rich visual representations and scalable grounding supervision. We present OPUS (\textbf{O}pen-vocabulary, \textbf{P}rompt-\textbf{U}nified, \textbf{S}

Read original source ↗ Open in workspace

recordType

paper

region

Global