LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

10/10/2022
by   Chenxi Liu, et al.
0

Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving. However, arguably due to the higher-dimensional nature of the data (as compared to images), existing neural architectures exhibit a large variety in their designs, including but not limited to the views considered, the format of the neural features, and the neural operations used. Lack of a unified framework and interpretation makes it hard to put these designs in perspective, as well as systematically explore new ones. In this paper, we begin by proposing a unified framework of such, with the key idea being factorizing the neural networks into a series of view transforms and neural layers. We demonstrate that this modular framework can reproduce a variety of existing works while allowing a fair comparison of backbone designs. Then, we show how this framework can easily materialize into a concrete neural architecture search (NAS) space, allowing a principled NAS-for-3D exploration. In performing evolutionary NAS on the 3D object detection task on the Waymo Open Dataset, not only do we outperform the state-of-the-art models, but also report the interesting finding that NAS tends to discover the same macro-level architecture concept for both the vehicle and pedestrian classes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2019

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

The state-of-the-art object detection method is complicated with various...
research
04/27/2022

PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search

Neural architecture search (NAS) aims to automate architecture engineeri...
research
08/13/2020

Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification

State-of-the-art speaker verification models are based on deep learning ...
research
12/16/2019

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Neural architecture search (NAS) aims to discover network architectures ...
research
08/26/2021

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

This work targets designing a principled and unified training-free frame...
research
08/09/2021

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

Neural architecture search (NAS), which automatically designs the archit...
research
07/23/2020

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

We address the curve lane detection problem which poses more realistic c...

Please sign up or login with your details

Forgot password? Click here to reset