.png){kind=icon}
返回
Constructing 3D Object Detectors Based on Deformable Convolutional Guided Depths
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3488748.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper introduces a depth-guided 3D object detection method that enhances the feature extraction capability of the backbone network through weak supervision. It combines large kernel convolution, global response normalization, and layer normalization techniques to significantly improve feature robustness under weakly supervised conditions. Additionally, the depth estimation module's feature extraction ability is bolstered by optimizing the depth-guided encoder and incorporating large-kernel depthwise separable convolutions alongside a spatial attention mechanism. On the decoder side, deformable convolutions are employed to modulate deep feature maps, reducing inference and training time while minimizing model complexity. This approach avoids the complexity associated with transformer architectures. Experiments on the KITTI 3D dataset demonstrate that the method diminishes reliance on manual labeling and can notably enhance detection accuracy while simultaneously improving processing speed.
Keyword:
Three-dimensional displays
Object detection
Feature extraction
Visualization
Solid modeling
Detectors
Transformers
Accuracy
Training
Kernel
Deep learning
Autonomous vehicles
3D object detection
deep learning
depth guidance
autonomous automobiles
model refinement
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Localization of myosin II to chromosome arms and spindle fibers in PtK1 cells: a possible role for an actomyosin system in mitosis.png)
Protoplasma
ProtoplasmaIF0
PREAI
分享收藏
EBCDet: Energy-Based Curriculum for Robust Domain Adaptive Object DetectionEBCDet: 基于能量的鲁棒域自适应目标检测课程IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容