计算机科学
人工智能
跳跃式监视
深度学习
判别式
目标检测
卷积神经网络
比例(比率)
卷积(计算机科学)
激光雷达
模式识别(心理学)
特征(语言学)
最小边界框
机器学习
计算机视觉
图像(数学)
人工神经网络
语言学
哲学
物理
遥感
量子力学
地质学
作者
Haiyang Jiang,Yuanyao Lu,Duona Zhang,Yuntao Shi,Jingxuan Wang
标识
DOI:10.1016/j.asoc.2024.111253
摘要
In the realm of autonomous driving, accurately detecting 3D objects is both vital and challenging. Recently, deep convolutional networks have been successfully implemented in the fusion of LiDAR and camera data, delivering impressive results. However, prevailing approaches tend to concentrate on basic architectural designs and the use of fixed 3D bounding boxes, overlooking the exploration of feature interrelations and the varying scales of 3D objects. In this paper, we propose High-order Attention Mechanism Fusion Networks (HAMFNs) for image expression and multi-scale learning, based on a novel high-order attention mechanism with multi-scale detection and scale linear regression. High-order convolution layers are built for tenser filtering with discriminative representations of the holistic image. Multi-scale query module further characterizes the saliency properties of the 3D objects. Our tests on the nuScenes dataset show that HAMFNs outperform the latest top-performing methods, achieving a 0.7% increase in mean Average Precision (mAP). We further integrated high-order convolutional layers into ResNet-50, ResNet-101, and ResNet-152 architectures, enhancing their performance with minimal parameter increase. The Top-1 error rates were reduced by 1.65%, 1.63%, and 1.60% for each network, respectively.
科研通智能强力驱动
Strongly Powered by AbleSci AI