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

• URL: http://arxiv.org/abs/2401.15865v1
• Date: Mon, 29 Jan 2024 03:35:55 GMT
• Title: LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
• Authors: Sifan Zhou, Liang Li, Xinyu Zhang, Bo Zhang, Shipeng Bai, Miao Sun, Ziyu Zhao, Xiaobo Lu, Xiangxiang Chu
• Abstract summary: Post-Training Quantization (PTQ) has been widely adopted in 2D vision tasks. LiDAR-PTQ can achieve state-of-the-art quantization performance when applied to CenterPoint. LiDAR-PTQ is cost-effective being $30times$ faster than the quantization-aware training method.
• Score: 35.35457515189062
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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, \textbf{(1)} a sparsity-based calibration method to determine the initialization of quantization parameters, \textbf{(2)} a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, \textbf{(3)} an adaptive rounding-to-nearest operation to minimize the layerwise reconstruction error. Extensive experiments demonstrate that our LiDAR-PTQ can achieve state-of-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 $3\times$ inference speedup. Moreover, our LiDAR-PTQ is cost-effective being $30\times$ faster than the quantization-aware training method. Code will be released at \url{https://github.com/StiphyJay/LiDAR-PTQ}.

Related papers

• GMS-3DQA: Projection-based Grid Mini-patch Sampling for 3D Model Quality Assessment [82.93561866101604]
  Previous projection-based 3DQA methods directly extract features from multi-projections to ensure quality prediction accuracy. We propose a no-reference (NR) projection-based textitunderlineGrid underlineMini-patch underlineSampling underline3D Model underlineQuality underlineAssessment (GMS-3DQA) method. The proposed GMS-3DQA requires far less computational resources and inference time than other 3D
  arXiv  Detail & Related papers  (2023-06-09T03:53:12Z)
• Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric [43.81334288840746]
  Post-Training Quantization (PTQ) transforms a full-precision model into low bit-width directly. PTQ suffers severe accuracy drop when applied to complex tasks such as object detection. DetPTQ employs the ODOL-based adaptive Lp metric to select the optimal quantization parameters.
  arXiv  Detail & Related papers  (2023-04-19T16:11:21Z)
• RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers [2.114921680609289]
  We propose RepQ-ViT, a novel PTQ framework for vision transformers (ViTs) RepQ-ViT decouples the quantization and inference processes. It can outperform existing strong baselines and encouragingly improve the accuracy of 4-bit PTQ of ViTs to a usable level.
  arXiv  Detail & Related papers  (2022-12-16T02:52:37Z)
• RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization [4.8018862391424095]
  We introduce a Power-of-Two post-training quantization( PTQ) method for deep neural network that meets hardware requirements. We propose a novel Power-of-Two PTQ framework, dubbed RAPQ, which dynamically adjusts the Power-of-Two scales of the whole network. We are the first to propose PTQ for the more constrained but hardware-friendly Power-of-Two quantization and prove that it can achieve nearly the same accuracy as SOTA PTQ method.
  arXiv  Detail & Related papers  (2022-04-26T14:02:04Z)
• Lite-FPN for Keypoint-based Monocular 3D Object Detection [18.03406686769539]
  Keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy trade-off. We propose a sort of lightweight feature pyramid network called Lite-FPN to achieve multi-scale feature fusion. Our proposed method achieves significantly higher accuracy and frame rate at the same time.
  arXiv  Detail & Related papers  (2021-05-01T14:44:31Z)
• PLUME: Efficient 3D Object Detection from Stereo Images [95.31278688164646]
  Existing methods tackle the problem in two steps: first depth estimation is performed, a pseudo LiDAR point cloud representation is computed from the depth estimates, and then object detection is performed in 3D space. We propose a model that unifies these two tasks in the same metric space. Our approach achieves state-of-the-art performance on the challenging KITTI benchmark, with significantly reduced inference time compared with existing methods.
  arXiv  Detail & Related papers  (2021-01-17T05:11:38Z)
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks [81.64530401885476]
  We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties. Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns. We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
  arXiv  Detail & Related papers  (2020-10-19T09:23:39Z)
• APQ: Joint Search for Network Architecture, Pruning and Quantization Policy [49.3037538647714]
  We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. With the same accuracy, APQ reduces the latency/energy by 2x/1.3x over MobileNetV2+HAQ.
  arXiv  Detail & Related papers  (2020-06-15T16:09:17Z)
• 3DSSD: Point-based 3D Single Stage Object Detector [61.67928229961813]
  We present a point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well.
  arXiv  Detail & Related papers  (2020-02-24T12:01:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.