RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917430971858944 |
|---|---|
| author | Hu, Guyue Song, Hao Tong, Yuxing Yuan, Duzhi Sun, Dengdi Zheng, Aihua Li, Chenglong Tang, Jin |
| author_facet | Hu, Guyue Song, Hao Tong, Yuxing Yuan, Duzhi Sun, Dengdi Zheng, Aihua Li, Chenglong Tang, Jin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20543 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images Hu, Guyue Song, Hao Tong, Yuxing Yuan, Duzhi Sun, Dengdi Zheng, Aihua Li, Chenglong Tang, Jin Computer Vision and Pattern Recognition 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. |
| title | RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.20543 |