# Rotated Object Detection via Scale-invariant Mahalanobis Distance in Aerial Images

arXiv: https://arxiv.org/abs/2204.00840 · HTML: https://mlsanity.com/paper/2204.00840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 2 Apr 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Learning Modulated Loss for Rotated Object Detection](https://mlsanity.com/paper/1911.08299/) (2019)
- [Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors](https://mlsanity.com/paper/2008.07043/) (2020)
- [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)

## Built on by (most cited first, 1 of 1)

- [A direct proof of a unified law of robustness for Bregman divergence losses](https://mlsanity.com/paper/2405.16639/) (2024)

## Abstract (arXiv)

Rotated object detection in aerial images is a meaningful yet challenging task as objects are densely arranged and have arbitrary orientations. The eight-parameter (coordinates of box vectors) methods in rotated object detection usually use ln-norm losses (L1 loss, L2 loss, and smooth L1 loss) as loss functions. As ln-norm losses are mainly based on non-scale-invariant Minkowski distance, using ln-norm losses will lead to inconsistency with the detection metric rotational Intersection-over-Union (IoU) and training instability. To address the problems, we use Mahalanobis distance to calculate loss between the predicted and the target box vertices' vectors, proposing a new loss function called Mahalanobis Distance Loss (MDL) for eight-parameter rotated object detection. As Mahalanobis distance is scale-invariant, MDL is more consistent with detection metric and more stable during training than ln-norm losses. To alleviate the problem of boundary discontinuity like all other eight-parameter methods, we further take the minimum loss value to make MDL continuous at boundary cases. We achieve state-of-art performance on DOTA-v1.0 with the proposed method MDL. Furthermore, compared to the experiment that uses smooth L1 loss, we find that MDL performs better in rotated object detection.