Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
By Xue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming, Wentao Wang, Qi Tian, Junchi Yan. Neural Information Processing Systems, 2021
567 citations recorded by the source corpus.
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection due to the limitation of current regression loss design, especially for objects with large aspect ratios. Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection. We show that one essential challenge is how to modulate the coupled parameters in the rotation regression loss, as such the estimated parameters can influence to each other during the dynamic joint optimization, in an adaptive and synergetic way. Specifically, we first convert the rotated bounding box into a 2-D Gaussian distribution, and then calculate the Kullback-Leibler Divergence (KLD) between the Gaussian distributions as the regression loss. By analyzing the gradient of each parameter, we show that KLD (and its derivatives) can dynamically adjust the parameter gradients according to the characteristics of the object. It will adjust the importance (gradient weight) of the angle parameter according to the aspect ratio. This mechanism can be vital for high-precision detection as a slight angle error would cause a serious accuracy drop for large aspect ratios objects. More importantly, we have proved that KLD is scale invariant. We further show that the KLD loss can be degenerated into the popular $l_{n}$-norm loss for horizontal detection. Experimental results on seven datasets using different detectors show its consistent superiority, and codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/c437bcc346b25004c1b47b39e3c1357735152144
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
- Large Selective Kernel Network for Remote Sensing Object Detection (2023, background): “Additionally, several loss functions, including GWD [77], KLD [79], and Modulated Loss [54], have been further proposed to enhance the Figure 1.”
- Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “Some others [4, 27, 72, 73] utilize Gaussian distributions to model the OBBs for object detection and de-sign new loss functions [51] to guide the learning process.”