Anchor-Free Oriented Proposal Generator for Object Detection

By Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, Junwei Han. IEEE Transactions on Geoscience and Remote Sensing, 2021

459 citations recorded by the source corpus.

Oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. However, the horizontal boxes are inclined to get small Intersection-over-Unions (IoUs) with ground truths, which may have some undesirable effects, such as introducing redundant noise, mismatching with ground truths, and detracting from the robustness of detectors. In this article, we propose a novel anchor-free oriented proposal generator (AOPG) that abandons horizontal box-related operations from the network architecture. AOPG first produces coarse oriented boxes by a coarse location module (CLM) in an anchor-free manner and then refines them into high-quality oriented proposals. After AOPG, we apply a Fast Region-based Convolutional Neural Network (R-CNN) head to produce the final detection results. Furthermore, the shortage of large-scale datasets is also a hindrance to the development of oriented object detection. To alleviate the data insufficiency, we release a new dataset on the basis of our DIOR dataset and name it DIOR-R. Massive experiments demonstrate the effectiveness of AOPG. Particularly, without bells and whistles, we achieve the accuracy of 64.41%, 75.24%, and 96.22% mAP on the DIOR-R, DOTA, and HRSC2016 datasets, respectively. Code and models are available at https://github.com/jbwang1997/AOPG.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9592cd57c517f22e5624ca6783e172cc436a1ced

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “5 [64], HRSC2016 [41], and DIOR-R [3] demonstrate the effectiveness of our method.”
Oriented RepPoints for Aerial Object Detection (2021, methodology): “[3] AOPG [2] Oriented RepPoints mAP 63.”
Advancing Plain Vision Transformer Toward Remote Sensing Foundation Model (2022, methodology): “0 [43] and DIOR-R [44] for evaluation.”
Large Selective Kernel Network for Remote Sensing Object Detection (2023, background): “AOPG [6] and R3Det [75] adopt a progressive regression approach, refining bounding boxes from coarse to fine granularity.”
GeoChat:Grounded Large Vision-Language Model for Remote Sensing (2023, methodology): “Specifically, we integrate three object detection (DOTA [34], DIOR [6], and FAIR1M [27] which together form the SAMRS [30] dataset), one scene classification (NWPU-RESISC-45 [5]), one VQA (LRBEN[20]), and one flood detection [25] VQA dataset (see Table 2).”
Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “Instead of restricting our scope to speciﬁc tasks, we investigate the related datasets which span over a wide range of research areas, including face detection [8], pedestrian detection [7], [148], [149], object detection in aerial images [20], [30], [160], [162], to name a few.”