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: this https URL.
Abstract (translated)
基于自然语言描述对特定对象进行分割的指代图像分割(RIS)在视觉-语言理解中扮演着重要角色。尽管其在遥感应用方面已取得进展,但在低空无人机(LAD)场景中的RIS研究仍然相对不足。现有的数据集和方法通常针对高空静态视图影像设计,难以处理LAD视角的特殊特性,如多样化的视角和高物体密度。为填补这一空白,我们推出了RIS-LAD,这是首个专为LAD场景量身定制的精细粒度RIS基准测试数据集。该数据集包含13,871组精心标注的图像-文本-掩码三元组,这些数据均来自真实的无人机视频,重点关注小尺寸、杂乱和多视角的场景。它强调了先前基准中未出现的新挑战,例如由微小物体引起的类别漂移以及在拥挤的同类物体背景下产生的对象漂移。 为解决这些问题,我们提出了语义感知自适应推理网络(SAARN)。不同于均匀注入所有语言特征,SAARN将语义信息分解并路由到网络的不同阶段。具体来说,“以类别为主导的语言增强”(CDLE)在早期编码中使视觉特征与物体类别对齐,“自适应推理融合模块”(ARFM)则跨尺度动态选择语义线索来改善复杂场景中的推理能力。 实验评估显示,RIS-LAD为最先进的RIS算法带来了重大挑战,并且证明了我们提出的模型在应对这些挑战方面的有效性。该数据集和代码将很快公开发布:[此链接](this https URL)。
URL
https://arxiv.org/abs/2507.20920