Timezone: »

Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
Jianhui Liu · Yukang Chen · Xiaoqing Ye · Zhuotao Tian · Xiao Tan · Xiaojuan Qi

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #217

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that 3D CNNs ignores the redundancy of data and further amplifies it in the down-sampling process, which brings a huge amount of extra and unnecessary computational overhead. Inspired by this, we propose a new convolution operator named spatial pruned sparse convolution (SPS-Conv), which includes two variants, spatial pruned submanifold sparse convolution (SPSS-Conv) and spatial pruned regular sparse convolution (SPRS-Conv), both of which are based on the idea of dynamically determine crucial areas for performing computations to reduce redundancy. We empirically find that magnitude of features can serve as an important cues to determine crucial areas which get rid of the heavy computations of learning-based methods. The proposed modules can easily be incorporated into existing sparse 3D CNNs without extra architectural modifications. Extensive experiments on the KITTI and nuScenes datasets demonstrate that our method can achieve more than 50% reduction in GFLOPs without compromising the performance.

Author Information

Jianhui Liu (The University of Hong Kong)
Yukang Chen (The Chinese University of Hong Kong)
Xiaoqing Ye (Baidu)
Zhuotao Tian (The Chinese University of Hong Kong)
Xiao Tan (Baidu Inc.)
Xiaojuan Qi (The University of Hong Kong)

More from the Same Authors