.png){kind=icon}
返回
Directional Alignment Instance Knowledge Distillation for Arbitrary-Oriented Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3307690.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, many lightweight neural networks have been deployed on airborne or satellite remote sensing platforms for real-time object detection. To bridge the performance gap between lightweight models and complex models, many knowledge distillation (KD) methods are investigated. However, existing KD methods ignore to transfer effective directional knowledge. Meanwhile, knowledge of different subtasks interferes with each other. To this end, a directional alignment instance knowledge distillation (DAIK) method for improving the performance of the lightweight object detection model is proposed. Specifically, an angle distillation (AD) module is developed to combine the circular smooth label (CSL) and teacher logits to transfer effective directional knowledge. Angular distance aspect ratio lookup table (AAL) is incorporated into label assignment and reweighting loss to enhance the prediction sensitivity of direction and shape in a discrete manner. Sample alignment distillation (SAD) reduces the spatial misalignment by mimicking the teacher model's distribution of anchor points. Extensive experiments are performed on several public remote sensing object detection datasets, which demonstrates the effectiveness of the proposed DAIK.
Keyword:
Knowledge distillation (KD)
real-time arbitrary-oriented object detection (AOOD)
remote sensing images
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection面向任意对象检测的通用高斯热图标签分配
OAAI
OAAI分享收藏Building a Bridge of Bounding Box Regression Between Oriented and Horizontal Object Detection in Remote Sensing Images在遥感图像中建立定向和水平目标检测之间的边界盒回归桥梁
PREAI
分享收藏
查看更多内容