# Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation arXiv: https://arxiv.org/abs/2409.11018 ยท HTML: https://mlsanity.com/paper/2409.11018/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). - Builds on 38 of its 50 references that are in the map. - First posted on arXiv 17 Sep 2024. ## Placed in - State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/) - Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/) ## Builds on (most cited first, 30 of 38) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023) - [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019) - [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020) - [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019) - [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018) - [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020) - [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017) - [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020) - [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018) - [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019) - [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019) - [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021) - [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023) - [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021) - [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018) - [SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2308.09244/) (2023) - [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022) - [DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets](https://mlsanity.com/paper/2301.06051/) (2023) - [Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds](https://mlsanity.com/paper/2203.10314/) (2022) - [SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction](https://mlsanity.com/paper/2404.09502/) (2024) - [SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2210.07372/) (2022) - [Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2207.10035/) (2022) - [One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation](https://mlsanity.com/paper/2310.19444/) (2023) - [From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels](https://mlsanity.com/paper/2303.13005/) (2023) - [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022) - [Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection](https://mlsanity.com/paper/2406.10700/) (2024) - [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://mlsanity.com/paper/2205.05979/) (2022) - [SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection](https://mlsanity.com/paper/2403.05817/) (2024) - [DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2309.15109/) (2023) ## Built on by (most cited first, 4 of 4) - [DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model](https://mlsanity.com/paper/2508.05402/) (2025) - [Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion](https://mlsanity.com/paper/2503.23721/) (2025) - [CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection](https://mlsanity.com/paper/2503.04154/) (2025) - [Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures](https://mlsanity.com/paper/2502.06189/) (2025) ## Abstract (arXiv) The LiDAR 3D object detector that balances accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR detection models rely on complex feature transformations, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a Faster LiDAR 3D object detection framework that Adaptively aligns Sparse voxels to enable efficient heterogeneous knowledge Distillation, called FASD. We aim to distill the Transformer's sequence modeling capability into Mamba models, significantly boosting accuracy through knowledge transfer. Specifically, we first design a cross-model knowledge distillation architecture to convey the global contextual understanding capabilities of the Transformer to Mamba. The Transformer-based teacher model employs a scale-adaptive attention mechanism to enhance multi-scale fusion. In contrast, the Mamba-based student model leverages feature alignment through spatial alignment adapters, supervised with latent-space features and span-head logit distributions, leading to improved performance and efficiency. We evaluated FASD on the Waymo and nuScenes datasets, achieving up to a 2x reduction in FLOPs and a 4x reduction in memory consumption, while improving baseline performance by 1-2 percentage points and maintaining high deployment efficiency.