RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images

• URL: http://arxiv.org/abs/2604.20543v2
• Date: Thu, 23 Apr 2026 07:42:41 GMT
• Title: RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images
• Abstract summary: This paper introduces a large-scale challenging dataset for referring detection in aerial images, termed as RefAerial.<n>It distinguishes from conventional ground referring detection datasets by 4 characteristics: (1) low but diverse object-to-scene ratios, (2) numerous targets and distractors, (3)complex and fine-grained referring descriptions, (4) diverse and broad scenes in the aerial view.
• Score: 26.44128761701781
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Referring detection refers to locate the target referred by natural languages, which has recently attracted growing research interests. However, existing datasets are limited to ground images with large object centered in relative small scenes. This paper introduces a large-scale challenging dataset for referring detection in aerial images, termed as RefAerial. It distinguishes from conventional ground referring detection datasets by 4 characteristics: (1) low but diverse object-to-scene ratios, (2) numerous targets and distractors, (3)complex and fine-grained referring descriptions, (4) diverse and broad scenes in the aerial view. We also develop a human-in-the-loop referring expansion and annotation engine (REA-Engine) for efficient semi-automated referring pair annotation. Besides, we observe that existing ground referring detection approaches exhibiting serious performance degradation on our aerial dataset since the intrinsic scale variety issue within or across aerial images. Therefore, we further propose a novel scale-comprehensive and sensitive (SCS) framework for referring detection in aerial images. It consists of a mixture-of-granularity (MoG) attention and a two-stage comprehensive-to-sensitive (CtS) decoding strategy. Specifically, the mixture-of-granularity attention is developed for scale-comprehensive target understanding. In addition, the two-stage comprehensive-to-sensitive decoding strategy is designed for coarse-to-fine referring target decoding. Eventually, the proposed SCS framework achieves remarkable performance on our aerial referring detection dataset and even promising performance boost on conventional ground referring detection datasets.

Related papers

• MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images [26.48439423478357]
  We introduce the first large-scale dataset for Multispectral Object Detection in Aerial images (MODA)<n>This dataset comprises 14,041 MSIs and 330,191 annotations across diverse, challenging scenarios.<n>We also propose OSSDet, a framework that integrates spectral and spatial information with object-aware cues.
  arXiv  Detail & Related papers  (2025-12-10T10:07:06Z)
• FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection [21.38164867490915]
  We propose a new family of real-time detectors for aerial image detection, named FBRT-YOLO, to address the imbalance between detection accuracy and efficiency.<n>FCM focuses on alleviating the problem of information imbalance caused by the loss of small target information in deep networks.<n>MKP, leverages convolutions with kernels of different sizes to enhance the relationships between targets of various scales.
  arXiv  Detail & Related papers  (2025-04-29T11:53:54Z)
• SAR Object Detection with Self-Supervised Pretraining and Curriculum-Aware Sampling [41.24071764578782]
  Object detection in satellite-borne Synthetic Aperture Radar imagery holds immense potential in tasks such as urban monitoring and disaster response.<n>The detection of small objects in satellite-borne SAR images poses a particularly intricate problem, because of the technology's relatively low spatial resolution and inherent noise.<n>In this paper, we introduce TRANSAR, a novel self-supervised end-to-end vision transformer-based SAR object detection model.
  arXiv  Detail & Related papers  (2025-04-17T19:44:05Z)
• AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations [51.44608822712786]
  Visual grounding aims to localize target objects in an image based on natural language descriptions.<n>AerialVG poses new challenges, emphe.g., appearance-based grounding is insufficient to distinguish among multiple visually similar objects.<n>We introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects.
  arXiv  Detail & Related papers  (2025-04-10T15:13:00Z)
• SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection [68.18620488664187]
  We propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++.<n> Specifically, we observe that objects from aerial images usually have arbitrary orientations, small scales, and dense distribution.<n>Extensive experiments conducted on various oriented object under various labeled settings demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-07-01T07:03:51Z)
• FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery [2.9687381456164004]
  This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery.<n>This research encompasses an array of methodologies including YOLO versions 5 and 8, Faster RCNN, CenterNet, RetinaNet, RTMDet, and DETR, all trained from scratch.<n>YOLOv5 emerges as a robust solution for aerial object detection, underlining its importance through superior mean average precision, Recall, and Intersection over Union scores.
  arXiv  Detail & Related papers  (2024-04-03T17:24:27Z)
• Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery [17.156864650143678]
  We develop a few-shot object detector based on a traditional two-stage architecture. A large-scale pre-trained model is used to build class-reference embeddings or prototypes. We perform evaluations on two remote sensing datasets containing challenging and rare objects.
  arXiv  Detail & Related papers  (2024-03-08T15:20:27Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• A Multi-purpose Real Haze Benchmark with Quantifiable Haze Levels and Ground Truth [61.90504318229845]
  This paper introduces the first paired real image benchmark dataset with hazy and haze-free images, and in-situ haze density measurements. This dataset was produced in a controlled environment with professional smoke generating machines that covered the entire scene. A subset of this dataset has been used for the Object Detection in Haze Track of CVPR UG2 2022 challenge.
  arXiv  Detail & Related papers  (2022-06-13T19:14:06Z)
• Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images [193.77450545067967]
  We propose an end-to-end Dense Attention Fluid Network (DAFNet) for salient object detection in optical remote sensing images (RSIs) A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships. We construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations.
  arXiv  Detail & Related papers  (2020-11-26T06:14:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.