Problem
Research questions and friction points this paper is trying to address.
BEV
multi-view 3D object detection
computational complexity
multi-scale feature extraction
dense 2D-to-BEV view transformation
Bi-Level Routing and Sparse Spatial Attention based Multi-View BEV 3D Object Detection for Autonomous Driving
🤖 AI Summary
为解决BEV 3D目标检测中的计算复杂度和效率问题，提出Sparse-BEVNet算法，通过引入Bi-Level Routing Attention和Cascaded Group Attention机制以及采用稀疏空间交叉注意力机制来提升性能。
📝 Abstract
Bird's Eye View (BEV)-based multi-view 3D object detection suffers from challenges of computational complexity, multi-scale feature extraction, and efficiency of dense 2D-to-BEV view transformation. To address these problems, this paper proposes an improved BEV 3D object detection algorithm Sparse-BEVNet. Firstly, a Bi-Level Routing Attention (BRA) mechanism is introduced into the image feature extraction network to reduce the computational burden of the backbone. Second, Cascaded Group Attention (CGA) is employed in the feature fusion module, which enhances deep interaction across features of different hierarchical levels without introducing additional computational overhead. Furthermore, a Sparse Spatial Cross-Attention mechanism is adopted to replace the conventional dense view projection pipeline. Experimental results on the public nuScenes dataset demonstrate that the proposed method achieves a mean Average Precision (mAP) of 45.2% and a nuScenes Detection Score (NDS) of 54.5%, corresponding to 3.6% and 2.8% improvements relative to the baseline model, respectively.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Bi-Level Routing Attention
Cascaded Group Attention
Sparse Spatial Cross-Attention
🔎 Similar Papers
No similar papers found.
