.png){kind=icon}
返回
Adaptive Angle Module and Radian Regression Method for Rotated Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2024.3381429.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Rotated object detectors commonly encounter instability during the training process, primarily due to background noise and angular periodicity. Targets with elongated or nonconvex shapes may introduce background noise during convolution, hindering accurately extracting features. Meanwhile, the periodicity of angles leads to predictions beyond the defined range, subsequently impeding the convergence. This letter introduces an angle adaptive module (AAM) designed for the backbone, enhancing the ability of the model to accurately extract object features and dynamically select the optimal angle. Moreover, to mitigate the effect of angle periodicity, a method called radian regression method (RRM) is proposed for predicting proper angles. It avoids directly regressing the value and instead produces the probability density distribution of the offset. We elaborately design numerous experiments to demonstrate the effectiveness of the proposed modules. As a result, the proposed method attains competitive results across various datasets, including DOTAv1.0, DOTAv1.5, DOTAv2.0, HRSC2016, and DIOR-R.
Keyword:
Feature extraction
Convolution
Detectors
Active appearance model
Training
Routing
Data mining
Aerial image
angle adaptive
radian regression method (RRM)
rotated object detector
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
A new series of vitamin D analogs is highly active for clonal inhibition, differentiation, and induction of WAF1 in myeloid leukemia.png)
Blood
OAAI
BloodIF0
OAAI分享收藏
分享收藏Decrease of autophagy activity promotes malignant progression of tongue squamous cell carcinoma自噬活性降低促进舌鳞状细胞癌恶性进展
PREAI
分享收藏
查看更多内容