LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

• URL: http://arxiv.org/abs/2501.04004v1
• Date: Tue, 07 Jan 2025 18:59:58 GMT
• Title: LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
• Authors: Xiang Xu, Lingdong Kong, Hui Shuai, Liang Pan, Ziwei Liu, Qingshan Liu,
• Abstract summary: LiMoE is a framework that integrates the Mixture of Experts (MoE) paradigm into LiDAR data representation learning. Our approach consists of three stages: Image-to-LiDAR Pretraining, Contrastive Mixture Learning (CML), and Semantic Mixture Supervision (SMS)
• Score: 55.33167217384738
• License:
• Abstract: LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focus on sparse voxel representation, overlooking the complementary attributes provided by other LiDAR representations. In this work, we propose LiMoE, a framework that integrates the Mixture of Experts (MoE) paradigm into LiDAR data representation learning to synergistically combine multiple representations, such as range images, sparse voxels, and raw points. Our approach consists of three stages: i) Image-to-LiDAR Pretraining, which transfers prior knowledge from images to point clouds across different representations; ii) Contrastive Mixture Learning (CML), which uses MoE to adaptively activate relevant attributes from each representation and distills these mixed features into a unified 3D network; iii) Semantic Mixture Supervision (SMS), which combines semantic logits from multiple representations to boost downstream segmentation performance. Extensive experiments across 11 large-scale LiDAR datasets demonstrate our effectiveness and superiority. The code and model checkpoints have been made publicly accessible.

Related papers

• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [52.83707400688378]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets. Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples. Our approach delivers significant performance improvements over state-of-the-art methods in both linear probing and fine-tuning tasks for both LiDAR-based segmentation and object detection.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving [58.16024314532443]
  We introduce LaserMix++, a framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to assist data-efficient learning. Results demonstrate that LaserMix++ outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.
  arXiv  Detail & Related papers  (2024-05-08T17:59:53Z)
• Multi-Space Alignments Towards Universal LiDAR Segmentation [50.992103482269016]
  M3Net is a one-of-a-kind framework for fulfilling multi-task, multi-dataset, multi-modality LiDAR segmentation. We first combine large-scale driving datasets acquired by different types of sensors from diverse scenes. We then conduct alignments in three spaces, namely data, feature, and label spaces, during the training.
  arXiv  Detail & Related papers  (2024-05-02T17:59:57Z)
• MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training [58.07391711548269]
  Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training. Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training.
  arXiv  Detail & Related papers  (2023-03-23T17:59:02Z)
• LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception [15.919789515451615]
  We introduce a new LiDAR multi-task learning paradigm based on the transformer. LiDARFormer exploits cross-task synergy to boost the performance of LiDAR perception tasks. LiDARFormer is evaluated on the large-scale nuScenes and the Open datasets for both 3D detection and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2023-03-21T20:52:02Z)
• Boosting 3D Object Detection by Simulating Multimodality on Point Clouds [51.87740119160152]
  This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors.
  arXiv  Detail & Related papers  (2022-06-30T01:44:30Z)

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.