OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
arxiv(2024)
摘要
The booming of 3D recognition in the 2020s began with the introduction of
point cloud transformers. They quickly overwhelmed sparse CNNs and became
state-of-the-art models, especially in 3D semantic segmentation. However,
sparse CNNs are still valuable networks, due to their efficiency treasure, and
ease of application. In this work, we reexamine the design distinctions and
test the limits of what a sparse CNN can achieve. We discover that the key
credit to the performance difference is adaptivity. Specifically, we propose
two key components, i.e., adaptive receptive fields (spatially) and adaptive
relation, to bridge the gap. This exploration led to the creation of
Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a
lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal
computational cost. Without any self-attention modules, OA-CNNs favorably
surpass point transformers in terms of accuracy in both indoor and outdoor
scenes, with much less latency and memory cost. Notably, it achieves 76.1
78.9
benchmarks respectively, while maintaining at most 5x better speed than
transformer counterparts. This revelation highlights the potential of pure
sparse CNNs to outperform transformer-related networks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要