TY - JOUR AU - Fan, Zhaoxin AU - Song, Zhenbo AU - Liu, Hongyan AU - Lu, Zhiwu AU - He, Jun AU - Du, Xiaoyong PY - 2022/06/28 Y2 - 2024/03/28 TI - SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 1 SE - AAAI Technical Track on Computer Vision I DO - 10.1609/aaai.v36i1.19934 UR - https://ojs.aaai.org/index.php/AAAI/article/view/19934 SP - 551-560 AB - Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both short-range local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0.8M and 0.4M respectively. ER -