Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/DevLinyan/Awesome-Knowledge-Distillation-for-Autonomous-Driving

A collection of papers about knowledge distillation in autonomous driving.
https://github.com/DevLinyan/Awesome-Knowledge-Distillation-for-Autonomous-Driving

List: Awesome-Knowledge-Distillation-for-Autonomous-Driving

3d-object-detection autonomous-driving knowledge-distillation

Last synced: 4 months ago
JSON representation

A collection of papers about knowledge distillation in autonomous driving.

Lists

README 

        
# Awesome Knowledge-Distillation for Autonomous Driving



- [Autonomous Driving](#awesome-knowledge-distillation)

  - [3D Object Detection](#3D-Object-Detection)

    - [Camera-only ](#Camera-only-Distillation)

    - [LiDAR-based ](#LiDAR-based-Distillation)



  - [Segmentation](#Segmentation)



  - [Auto Labeling](#Auto-Labeling)



## 3D Object Detection



### Camera-only Distillation



1. Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection. [NeurIPS 2023](https://arxiv.org/abs/2310.15670) [[Official Code]](https://github.com/OpenDriveLab/Birds-eye-view-Perception/tree/master/nuScenes_playground/VCD)



2. BEVSimDet: Simulated Multi-modal Distillation in Bird's-Eye View for Multi-view 3D Object Detection. [Arxiv 2023](https://arxiv.org/abs/2303.16818) [[Official Code]](https://github.com/ViTAE-Transformer/BEVSimDet)



3. Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection. [CVPR 2023](https://openaccess.thecvf.com/content/CVPR2023/html/Zeng_Distilling_Focal_Knowledge_From_Imperfect_Expert_for_3D_Object_Detection_CVPR_2023_paper.html) [[Official Code]](https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/master/nuScenes_playground/FocalDistiller.md)



4. UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View. [CVPR 2023](https://arxiv.org/abs/2303.15083) [[Official Code]](https://github.com/megvii-research/CVPR2023-UniDistill)



5. X $^3$ KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection. [CVPR 2023](https://arxiv.org/abs/2303.02203)



6. BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection. [ICLR 2023](https://arxiv.org/abs/2211.09386) [[Official Code]](https://github.com/zehuichen123/BEVDistill)



7. BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection.  [Arxiv 2022](https://arxiv.org/abs/2212.00623)



8. TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning. [Arxiv 2022](https://arxiv.org/abs/2212.13979) [[Official Code]](https://github.com/ADLab3Ds/TiG-BEV)



9. Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection. [Arxiv 2022](https://arxiv.org/abs/2211.08398)



10. Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection. [ECCV 2022](https://arxiv.org/abs/2211.07171) [[Official Code]](https://github.com/Cc-Hy/CMKD)



11. Lidar Point Cloud Guided Monocular 3D Object Detection. [ECCV 2022](https://arxiv.org/abs/2104.09035) [[Official Code]](https://github.com/SPengLiang/LPCG)



12. LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector. [ICCV 2021](https://arxiv.org/abs/2108.08258) [[Official Code]](https://github.com/xy-guo/LIGA-Stereo)



### LiDAR-based Distillation



1. Representation Disparity-aware Distillation for 3D Object Detection. [ICCV 2023](https://openaccess.thecvf.com/content/ICCV2023/html/Li_Representation_Disparity-aware_Distillation_for_3D_Object_Detection_ICCV_2023_paper.html)



2. itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection. [CVPR 2023](https://arxiv.org/abs/2205.15531)



3. PointDistiller: Structured Knowledge Distillation TowardsEfficient and Compact 3D Detection. [CVPR 2023](https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_PointDistiller_Structured_Knowledge_Distillation_Towards_Efficient_and_Compact_3D_Detection_CVPR_2023_paper.html) [[Official Code]](https://github.com/RunpeiDong/PointDistiller)



4. Towards Efficient 3D Object Detection withKnowledge Distillation. [NeurIPS 2022](https://proceedings.neurips.cc/paper_files/paper/2022/hash/8625a8c2be8ba5197b7a14833dbea8ac-Abstract-Conference.html) [[Official Code]](https://github.com/CVMI-Lab/SparseKD)



5. LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection. [ECCV 2022](https://arxiv.org/abs/2203.14956) [[Official Code]](https://github.com/weiyithu/LiDAR-Distillation)



### Pretraining Distillation

1. Geometric-aware Pretraining for Vision-centric 3D Object Detection. [Arxiv 2023](https://arxiv.org/abs/2304.03105) [[Official Code]](https://github.com/OpenDriveLab/Birds-eye-view-Perception/tree/master/nuScenes_playground)



2. Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding. [ICCV 2023](https://arxiv.org/abs/2303.11325) [[Official Code]](https://github.com/Sense-X/GeoMIM)



## Segmentation



1. Segment Any Point Cloud Sequences by Distilling Vision Foundation Models. [NeurIPS 2023](https://arxiv.org/abs/2306.09347) [[Official Code]](https://github.com/youquanl/Segment-Any-Point-Cloud)



2. Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data. [CVPR 2022](https://arxiv.org/abs/2203.16258) [[Official Code]]( https://github.com/valeoai/SLidR)



##  Auto Labeling



1. Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving. [ICCV 2023](https://arxiv.org/abs/2309.14491)



---

Note: All papers' pdf can be found and downloaded on [arXiv](https://arxiv.org/search/), [Google](https://www.google.com) or [Bing](https://www.bing.com).