Monocular 3D Target Detection Model Based on Differential Neural Network Architecture Search
Xiaofeng Yang, Tianzhu Liang, Shengli Lu · Journal of Physics Conference Series · 2023
Abstract This paper explores the possibility of applying neural network architecture search to monocular 3D target detection tasks, so as to solve the problem that researchers need a lot of time and prior knowledge to manually design network structures. The algorithm applies the differentiable neural network architecture search technology to the backbones search of the 3D monocular target detection network FCOS3D. At the same time, to improve the accuracy of the algorithm for 3D target detection tasks and reduce the computational complexity of the algorithm, we add deformable convolution and depth separable convolution to the network searchable space. Finally, our algorithm is superior to the original FCOS3D algorithm in the KITTI3D monocular target detection dataset.