RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentation

TL;DR

This paper introduces RIS-LAD, a new benchmark dataset for referring image segmentation in low-altitude drone scenarios, along with a novel model SAARN that improves segmentation by semantic-aware reasoning.

Contribution

It provides the first fine-grained RIS benchmark for LAD scenes and proposes SAARN, a model that enhances segmentation by decomposing and routing semantic information adaptively.

Findings

RIS-LAD presents new challenges for RIS algorithms.

SAARN outperforms existing methods on RIS-LAD.

The dataset and model advance vision-language understanding in drone imagery.

Abstract

Referring Image Segmentation (RIS), which aims to segment specific objects based on natural language descriptions, plays an essential role in vision-language understanding. Despite its progress in remote sensing applications, RIS in Low-Altitude Drone (LAD) scenarios remains underexplored. Existing datasets and methods are typically designed for high-altitude and static-view imagery. They struggle to handle the unique characteristics of LAD views, such as diverse viewpoints and high object density. To fill this gap, we present RIS-LAD, the first fine-grained RIS benchmark tailored for LAD scenarios. This dataset comprises 13,871 carefully annotated image-text-mask triplets collected from realistic drone footage, with a focus on small, cluttered, and multi-viewpoint scenes. It highlights new challenges absent in previous benchmarks, such as category drift caused by tiny objects and object drift under crowded same-class objects. To tackle these issues, we propose the Semantic-Aware Adaptive Reasoning Network (SAARN). Rather than uniformly injecting all linguistic features, SAARN decomposes and routes semantic information to different stages of the network. Specifically, the Category-Dominated Linguistic Enhancement (CDLE) aligns visual features with object categories during early encoding, while the Adaptive Reasoning Fusion Module (ARFM) dynamically selects semantic cues across scales to improve reasoning in complex scenes. The experimental evaluation reveals that RIS-LAD presents substantial challenges to state-of-the-art RIS algorithms, and also demonstrates the effectiveness of our proposed model in addressing these challenges. The dataset and code will be publicly released soon at: https://github.com/AHideoKuzeA/RIS-LAD/.