# Learning Modulated Loss for Rotated Object Detection

arXiv: https://arxiv.org/abs/1911.08299 · HTML: https://mlsanity.com/paper/1911.08299/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 30 of 73)

- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [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)
- [Poly Kernel Inception Network for Remote Sensing Detection](https://mlsanity.com/paper/2403.06258/) (2024)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection](https://mlsanity.com/paper/2211.06368/) (2022)
- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://mlsanity.com/paper/2209.10839/) (2022)
- [GLASS: Global to Local Attention for Scene-Text Spotting](https://mlsanity.com/paper/2208.03364/) (2022)
- [H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection](https://mlsanity.com/paper/2304.04403/) (2023)
- [Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss](https://mlsanity.com/paper/2103.11636/) (2021)
- [A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2109.12848/) (2021)
- [Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision](https://mlsanity.com/paper/2311.14758/) (2023)
- [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)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery](https://mlsanity.com/paper/2312.02481/) (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)
- [Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection](https://mlsanity.com/paper/2501.03775/) (2025)
- [GRA: Detecting Oriented Objects through Group-wise Rotating and Attention](https://mlsanity.com/paper/2403.11127/) (2024)
- [PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection](https://mlsanity.com/paper/2410.08210/) (2024)
- [SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection](https://mlsanity.com/paper/2407.01016/) (2024)
- [Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances](https://mlsanity.com/paper/2502.04268/) (2025)

## Abstract (arXiv)

Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the aforementioned integration can cause training instability and performance degeneration, due to the loss discontinuity resulted from the inherent periodicity of angles and the associated sudden exchange of width and height. This problem is further pronounced given the regression inconsistency among five parameters with different measurement units. We refer to the above issues as rotation sensitivity error (RSE) and propose a modulated rotation loss to dismiss the loss discontinuity. Our new loss is combined with the eight-parameter regression to further solve the problem of inconsistent parameter regression. Experiments show the state-of-art performances of our method on the public aerial image benchmark DOTA and UCAS-AOD. Its generalization abilities are also verified on ICDAR2015, HRSC2016, and FDDB. Qualitative improvements can be seen in Fig 1, and the source code will be released with the publication of the paper.