# Towards Efficient 3D Object Detection with Knowledge Distillation

arXiv: https://arxiv.org/abs/2205.15156 · HTML: https://mlsanity.com/paper/2205.15156/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 54 of its 72 references that are in the map.
- First posted on arXiv 30 May 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 54)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [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)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (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)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)

## Built on by (most cited first, 29 of 29)

- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)
- [Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation](https://mlsanity.com/paper/2404.11958/) (2024)
- [X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection](https://mlsanity.com/paper/2303.02203/) (2023)
- [RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features](https://mlsanity.com/paper/2403.05061/) (2024)
- [CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation](https://mlsanity.com/paper/2403.19104/) (2024)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection](https://mlsanity.com/paper/2205.15531/) (2022)
- [TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2407.09751/) (2024)
- [Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection](https://mlsanity.com/paper/2402.18493/) (2024)
- [SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation](https://mlsanity.com/paper/2506.17290/) (2025)
- [Geometric-aware Pretraining for Vision-centric 3D Object Detection](https://mlsanity.com/paper/2304.03105/) (2023)
- [StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection](https://mlsanity.com/paper/2301.01615/) (2023)
- [Weak-to-Strong 3D Object Detection with X-Ray Distillation](https://mlsanity.com/paper/2404.00679/) (2024)
- [PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest](https://mlsanity.com/paper/2403.09212/) (2024)
- [Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation](https://mlsanity.com/paper/2409.11018/) (2024)
- [Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection](https://mlsanity.com/paper/2211.08398/) (2022)
- [Representation Disparity-aware Distillation for 3D Object Detection](https://mlsanity.com/paper/2308.10308/) (2023)
- [LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration](https://mlsanity.com/paper/2310.03669/) (2023)
- [LEROjD: Lidar Extended Radar-Only Object Detection](https://mlsanity.com/paper/2409.05564/) (2024)
- [Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds](https://mlsanity.com/paper/2505.17442/) (2025)
- [Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals](https://mlsanity.com/paper/2308.08125/) (2023)
- [Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment](https://mlsanity.com/paper/2312.00663/) (2023)
- [MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector](https://mlsanity.com/paper/2405.15176/) (2024)
- [Semantic-Supervised Spatial-Temporal Fusion for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2503.10579/) (2025)
- [Smaller3d: Smaller Models for 3D Semantic Segmentation Using Minkowski Engine and Knowledge Distillation Methods](https://mlsanity.com/paper/2305.03188/) (2023)
- [IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion](https://mlsanity.com/paper/2512.15581/) (2025)
- [Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation](https://mlsanity.com/paper/2606.25278/) (2026)
- [Lightweight 3D Object Detection via Mamba-Based Knowledge Distillation](https://mlsanity.com/paper/2608.03490/) (2026)

## Abstract (arXiv)

Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential of knowledge distillation (KD) for developing efficient 3D object detectors, focusing on popular pillar- and voxel-based detectors.In the absence of well-developed teacher-student pairs, we first study how to obtain student models with good trade offs between accuracy and efficiency from the perspectives of model compression and input resolution reduction. Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs. Further, we propose an improved KD pipeline incorporating an enhanced logit KD method that performs KD on only a few pivotal positions determined by teacher classification response, and a teacher-guided student model initialization to facilitate transferring teacher model's feature extraction ability to students through weight inheritance. Finally, we conduct extensive experiments on the Waymo dataset. Our best performing model achieves 65.75% LEVEL 2 mAPH, surpassing its teacher model and requiring only 44% of teacher flops. Our most efficient model runs 51 FPS on an NVIDIA A100, which is 2.2× faster than PointPillar with even higher accuracy. Code is available at urlhttps://github.com/CVMI-Lab/SparseKD.