SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.15865 · ICLR · 2024

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

Bo Zhang, Xiangxiang Chu, Shipeng Bai, Liang Li, Xinyu Zhang, Sifan Zhou, Miao Sun, Ziyu Zhao, Xiaobo Lu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression approach, Post-Training Quantization (PTQ) has been widely adopted in 2D vision tasks. However, applying it directly to 3D lidar-based tasks inevitably leads to performance degradation. As a remedy, we propose an effective PTQ method called LiDAR-PTQ, which is particularly curated for 3D lidar detection (both SPConv-based and SPConv-free). Our LiDAR-PTQ features three main components, (1) a sparsity-based calibration method to determine the initialization of quantization parameters, (2) a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, (3) an adaptive rounding-to-nearest operation to minimize the layerwise reconstruction error. Extensive experiments demonstrate that our LiDAR-PTQ can achieve stateof-the-art quantization performance when applied to CenterPoint (both Pillar-based and Voxel-based). To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying 3× inference speedup. Moreover, our LiDAR-PTQ is costeffective being 30× faster than the quantization-aware training method. Code will be released at https://github.com/StiphyJay/LiDAR-PTQ.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.15865")
get_code_for_paper("2401.15865")
have("2401.15865")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.15865.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.15865.svg)](https://syntology.ai/paper/2401.15865)

Connect an agent — have() is free.