Paper Reading AI Learner

A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding

2025-05-28 04:28:13
Mengjingcheng Mo, Xinyang Tong, Jiaxu Leng, Mingpi Tan, Jiankang Zheng, Yiran Liu, Haosheng Chen, Ji Gan, Weisheng Li, Xinbo Gao

Abstract

While unmanned aerial vehicles (UAVs) offer wide-area, high-altitude coverage for anomaly detection, they face challenges such as dynamic viewpoints, scale variations, and complex scenes. Existing datasets and methods, mainly designed for fixed ground-level views, struggle to adapt to these conditions, leading to significant performance drops in drone-view scenarios. To bridge this gap, we introduce A2Seek (Aerial Anomaly Seek), a large-scale, reasoning-centric benchmark dataset for aerial anomaly understanding. This dataset covers various scenarios and environmental conditions, providing high-resolution real-world aerial videos with detailed annotations, including anomaly categories, frame-level timestamps, region-level bounding boxes, and natural language explanations for causal reasoning. Building on this dataset, we propose A2Seek-R1, a novel reasoning framework that generalizes R1-style strategies to aerial anomaly understanding, enabling a deeper understanding of "Where" anomalies occur and "Why" they happen in aerial frames. To this end, A2Seek-R1 first employs a graph-of-thought (GoT)-guided supervised fine-tuning approach to activate the model's latent reasoning capabilities on A2Seek. Then, we introduce Aerial Group Relative Policy Optimization (A-GRPO) to design rule-based reward functions tailored to aerial scenarios. Furthermore, we propose a novel "seeking" mechanism that simulates UAV flight behavior by directing the model's attention to informative regions. Extensive experiments demonstrate that A2Seek-R1 achieves up to a 22.04% improvement in AP for prediction accuracy and a 13.9% gain in mIoU for anomaly localization, exhibiting strong generalization across complex environments and out-of-distribution scenarios. Our dataset and code will be released at this https URL.

Abstract (translated)

尽管无人驾驶飞行器(无人机)能够提供广泛区域和高空的异常检测覆盖,但它们面临诸如动态视角、尺度变化及复杂场景等挑战。现有的数据集和方法主要针对固定的地面级视图设计,难以适应这些条件,在无人机视角的应用场景中导致性能大幅下降。为解决这一差距,我们推出了A2Seek(Aerial Anomaly Seek),这是一个大规模、以推理为中心的基准数据集,旨在用于空中异常理解。该数据集涵盖了多种场景和环境条件,并提供了高分辨率的真实世界空域视频以及详细的注释,包括异常类别、帧级别的时间戳、区域级别的边界框和自然语言解释,用于因果关系推理。 基于此数据集,我们提出了A2Seek-R1,这是一种新颖的推理框架,它将R1风格策略推广到空中异常理解领域,使模型能够更深入地理解“在哪里”发生了异常以及“为什么”会发生这些异常。为此,A2Seek-R1首先采用了一种图思维(GoT)引导的监督微调方法来激活模型在A2Seek上的潜在推理能力。接着,我们引入了空中群体相对策略优化(A-GRPO),以设计适用于空中场景的规则化奖励函数。此外,我们还提出了一种新颖的“寻找”机制,通过将模型注意力集中到信息丰富的区域上来模拟无人机飞行行为。 广泛的实验表明,A2Seek-R1在预测准确率上达到了高达22.04%的AP(平均精度)改进,在异常定位上的mIoU(平均交并比)提升了13.9%,展示了其在复杂环境和分布外场景中的强大泛化能力。我们的数据集和代码将在[提供的URL]处发布。

URL

https://arxiv.org/abs/2505.21962

PDF

https://arxiv.org/pdf/2505.21962.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot