# Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss

arXiv: https://arxiv.org/abs/2103.11636 · HTML: https://mlsanity.com/paper/2103.11636/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://mlsanity.com/paper/1703.01086/) (2017)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Gliding vertex on the horizontal bounding box for multi-oriented object detection](https://mlsanity.com/paper/1911.09358/) (2019)
- [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://mlsanity.com/paper/1801.02765/) (2018)
- [Rotation-Sensitive Regression for Oriented Scene Text Detection](https://mlsanity.com/paper/1803.05265/) (2018)
- [Dense Label Encoding for Boundary Discontinuity Free Rotation Detection](https://mlsanity.com/paper/2011.09670/) (2020)
- [Learning Modulated Loss for Rotated Object Detection](https://mlsanity.com/paper/1911.08299/) (2019)
- [Dynamic Refinement Network for Oriented and Densely Packed Object Detection](https://mlsanity.com/paper/2005.09973/) (2020)
- [Dynamic Anchor Learning for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2012.04150/) (2020)
- [Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors](https://mlsanity.com/paper/2008.07043/) (2020)
- [SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing](https://mlsanity.com/paper/2004.13316/) (2020)
- [Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks](https://mlsanity.com/paper/1806.04331/) (2018)
- [R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection](https://mlsanity.com/paper/1706.09579/) (2017)
- [Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery](https://mlsanity.com/paper/1807.02700/) (2018)
- [CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery](https://mlsanity.com/paper/1903.00857/) (2019)
- [Oriented Objects as pairs of Middle Lines](https://mlsanity.com/paper/1912.10694/) (2019)
- [Single Shot Text Detector with Regional Attention](https://mlsanity.com/paper/1709.00138/) (2017)
- [CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2101.06849/) (2021)
- [Omnidirectional Scene Text Detection with Sequential-free Box Discretization](https://mlsanity.com/paper/1906.02371/) (2019)
- [Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks](https://mlsanity.com/paper/1804.06039/) (2018)

## Built on by (most cited first, 27 of 27)

- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection](https://mlsanity.com/paper/2203.15221/) (2022)
- [Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer](https://mlsanity.com/paper/2202.05508/) (2022)
- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://mlsanity.com/paper/2209.10839/) (2022)
- [G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2205.11796/) (2022)
- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection](https://mlsanity.com/paper/2109.11906/) (2021)
- [Rethinking Boundary Discontinuity Problem for Oriented Object Detection](https://mlsanity.com/paper/2305.10061/) (2023)
- [Theoretically Achieving Continuous Representation of Oriented Bounding Boxes](https://mlsanity.com/paper/2402.18975/) (2024)
- [Multi-Grained Angle Representation for Remote Sensing Object Detection](https://mlsanity.com/paper/2209.02884/) (2022)
- [GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection](https://mlsanity.com/paper/2502.01565/) (2025)
- [Transformation-Invariant Network for Few-Shot Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2303.06817/) (2023)
- [DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection](https://mlsanity.com/paper/2109.06148/) (2021)
- [PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection](https://mlsanity.com/paper/2312.10515/) (2023)
- [Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detection](https://mlsanity.com/paper/2311.05410/) (2023)
- [Unitail: Detecting, Reading, and Matching in Retail Scene](https://mlsanity.com/paper/2204.00298/) (2022)
- [Oriented Feature Alignment for Fine-grained Object Recognition in High-Resolution Satellite Imagery](https://mlsanity.com/paper/2110.06628/) (2021)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [Learning to Reduce Information Bottleneck for Object Detection in Aerial Images](https://mlsanity.com/paper/2204.02033/) (2022)
- [ABFL: Angular Boundary Discontinuity Free Loss for Arbitrary Oriented Object Detection in Aerial Images](https://mlsanity.com/paper/2311.12311/) (2023)
- [MKIoU Loss: Towards Accurate Oriented Object Detection in Aerial Images](https://mlsanity.com/paper/2206.15109/) (2022)
- [Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images](https://mlsanity.com/paper/2209.02200/) (2022)
- [Metric-aligned Sample Selection and Critical Feature Sampling for Oriented Object Detection](https://mlsanity.com/paper/2306.16718/) (2023)
- [FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection](https://mlsanity.com/paper/2405.09942/) (2024)
- [Efficient Oriented Object Detection with Enhanced Small Object Recognition in Aerial Images](https://mlsanity.com/paper/2412.12562/) (2024)
- [LOGOS: Language-guided Oriented Object Detection in Aerial Scenes](https://mlsanity.com/paper/2607.08004/) (2026)

## Abstract (arXiv)

Arbitrary-oriented objects exist widely in natural scenes, and thus the oriented object detection has received extensive attention in recent years. The mainstream rotation detectors use oriented bounding boxes (OBB) or quadrilateral bounding boxes (QBB) to represent the rotating objects. However, these methods suffer from the representation ambiguity for oriented object definition, which leads to suboptimal regression optimization and the inconsistency between the loss metric and the localization accuracy of the predictions. In this paper, we propose a Representation Invariance Loss (RIL) to optimize the bounding box regression for the rotating objects. Specifically, RIL treats multiple representations of an oriented object as multiple equivalent local minima, and hence transforms bounding box regression into an adaptive matching process with these local minima. Then, the Hungarian matching algorithm is adopted to obtain the optimal regression strategy. We also propose a normalized rotation loss to alleviate the weak correlation between different variables and their unbalanced loss contribution in OBB representation. Extensive experiments on remote sensing datasets and scene text datasets show that our method achieves consistent and substantial improvement. The source code and trained models are available at https://github.com/ming71/RIDet.