Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection

TL;DR

This paper introduces OTA-Det, a unified framework that combines aerial visual grounding and detection, enabling rich semantic understanding and multi-target detection with real-time performance.

Contribution

It presents the first unified architecture that bridges OVAD and RSVG, allowing joint training and fine-grained semantic alignment for aerial scene understanding.

Findings

Achieves state-of-the-art results on six benchmarks.

Supports real-time inference at 34 FPS.

Enables dense semantic understanding at multiple granularities.

Abstract

Open-Vocabulary Aerial Detection (OVAD) and Remote Sensing Visual Grounding (RSVG) have emerged as two key paradigms for aerial scene understanding. However, each paradigm suffers from inherent limitations when operating in isolation: OVAD is restricted to coarse category-level semantics, while RSVG is structurally limited to single-target localization. These limitations prevent existing methods from simultaneously supporting rich semantic understanding and multi-target detection. To address this, we propose OTA-Det, the first unified framework that bridges both paradigms into a cohesive architecture. Specifically, we introduce a task reformulation strategy that unifies task objectives and supervision mechanisms, enabling joint training across datasets from both paradigms with dense supervision signals. Furthermore, we propose a dense semantic alignment strategy that establishes explicit correspondence at multiple granularities, from holistic expressions to individual attributes, enabling fine-grained semantic understanding. To ensure real-time efficiency, OTA-Det builds upon the RT-DETR architecture, extending it from closed-set detection to open-text detection by introducing several high efficient modules, achieving state-of-the-art performance on six benchmarks spanning both OVAD and RSVG tasks while maintaining real-time inference at 34 FPS.