PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
원문 초록
3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resources on edge devices make these requirements rather challenging. Previous work processes 3D data using either voxel-based or point-based neural networks, but both types of 3D models are not hardware-efficient due to the large memory footprint and random memory access. In this paper, we study 3D deep learning from the efficiency perspective. We first systematically analyze the bottlenecks of previous 3D methods. We then combine the best from point-based and voxel-based models together and propose a novel hardware-efficient 3D primitive, Point-Voxel Convolution (PVConv). We further enhance this primitive with the sparse convolution to make it more effective in processing large (outdoor) scenes. Based on our designed 3D primitive, we introduce 3D Neural Architecture Search (3D-NAS) to explore the best 3D network architecture given a resource constraint. We evaluate our proposed method on six representative benchmark datasets, achieving state-of-the-art performance with 1.8-23.7x measured speedup. Furthermore, our method has been deployed to the autonomous racing vehicle of MIT Driverless, achieving larger detection range, higher accuracy and lower latency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing
From Tiny Machine Learning to Tiny Deep Learning: A Survey
Structured Pruning and Quantization for Learned Image Compression
Gibbs randomness-compression proposition: An efficient deep learning
Optimizing edge AI models on HPC systems with the edge in the loop
토론
이 논문과 연결된 포럼 글이 아직 없습니다.