# Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

arXiv: https://arxiv.org/abs/1812.00155 · HTML: https://mlsanity.com/paper/1812.00155/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2018.

## Built on by (most cited first, 30 of 37)

- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [EarthNets: Empowering AI in Earth Observation](https://mlsanity.com/paper/2210.04936/) (2022)
- [HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images](https://mlsanity.com/paper/2404.09178/) (2024)
- [DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing](https://mlsanity.com/paper/2407.08132/) (2024)
- [There Are No Data Like More Data- Datasets for Deep Learning in Earth Observation](https://mlsanity.com/paper/2310.19231/) (2023)
- [Interactive Multi-Class Tiny-Object Detection](https://mlsanity.com/paper/2203.15266/) (2022)
- [CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos](https://mlsanity.com/paper/2406.01029/) (2024)
- [OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction](https://mlsanity.com/paper/2410.23278/) (2024)
- [Arbitrary-Oriented Ship Detection through Center-Head Point Extraction](https://mlsanity.com/paper/2101.11189/) (2021)
- [RemDet: Rethinking Efficient Model Design for UAV Object Detection](https://mlsanity.com/paper/2412.10040/) (2024)
- [SARMAE: Masked Autoencoder for SAR Representation Learning](https://mlsanity.com/paper/2512.16635/) (2025)
- [Graph Fusion Network for Multi-Oriented Object Detection](https://mlsanity.com/paper/2205.03562/) (2022)
- [Self-Training Guided Disentangled Adaptation for Cross-Domain Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2301.05526/) (2023)
- [All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification](https://mlsanity.com/paper/2205.03371/) (2022)
- [Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2107.11758/) (2021)
- [Aerial Image Object Detection With Vision Transformer Detector (ViTDet)](https://mlsanity.com/paper/2301.12058/) (2023)
- [SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing](https://mlsanity.com/paper/2410.13471/) (2024)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Diminishing Domain Bias by Leveraging Domain Labels in Object Detection on UAVs](https://mlsanity.com/paper/2101.12677/) (2021)
- [ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera](https://mlsanity.com/paper/2201.10107/) (2022)
- [View-Invariant Localization using Semantic Objects in Changing Environments](https://mlsanity.com/paper/2209.14426/) (2022)
- [Centerpoints Are All You Need in Overhead Imagery](https://mlsanity.com/paper/2210.01857/) (2022)
- [Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap](https://mlsanity.com/paper/2202.06565/) (2022)
- [Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach](https://mlsanity.com/paper/2412.10453/) (2024)
- [Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision](https://mlsanity.com/paper/2508.03745/) (2025)
- [Counting Objects by Diffused Index: geometry-free and training-free approach](https://mlsanity.com/paper/2110.08365/) (2021)
- [A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification](https://mlsanity.com/paper/2203.16325/) (2022)
- [Learning Instance Representation Banks for Aerial Scene Classification](https://mlsanity.com/paper/2205.13744/) (2022)
- [Object Detection in Aerial Images with Uncertainty-Aware Graph Network](https://mlsanity.com/paper/2208.10781/) (2022)
- [Object Detection performance variation on compressed satellite image datasets with iquaflow](https://mlsanity.com/paper/2301.05892/) (2023)

## Abstract (arXiv)

Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design of them always multiplies the number of anchors and dramatically increases the computational complexity. In this paper, we propose a RoI Transformer to address these problems. More precisely, to improve the quality of region proposals, we first designed a Rotated RoI (RRoI) learner to transform a Horizontal Region of Interest (HRoI) into a Rotated Region of Interest (RRoI). Based on the RRoIs, we then proposed a Rotated Position Sensitive RoI Align (RPS-RoI-Align) module to extract rotation-invariant features from them for boosting subsequent classification and regression. Our RoI Transformer is with light weight and can be easily embedded into detectors for oriented object detection. A simple implementation of the RoI Transformer has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer. The results demonstrate that it can be easily integrated with other detector architectures and significantly improve the performances.