# Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2603.07464 · HTML: https://mlsanity.com/paper/2603.07464/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 53 of its 73 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## 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 53)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (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)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [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)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [Disentangling Monocular 3D Object Detection](https://mlsanity.com/paper/1905.12365/) (2019)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [A Survey on Negative Transfer](https://mlsanity.com/paper/2009.00909/) (2020)
- [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)

## Abstract (arXiv)

Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information from LiDAR to image-based network. However, modality gap between image and LiDAR seriously limits its accuracy. In this paper, we systematically investigate the negative transfer problem induced by modality gap in cross-modality distillation for the first time, including not only the architecture inconsistency issue but more importantly the feature overfitting issue. We propose a selective learning approach named MonoSTL to overcome these issues, which encourages positive transfer of depth information from LiDAR while alleviates the negative transfer on image-based network. On the one hand, we utilize similar architectures to ensure spatial alignment of features between image-based and LiDAR-based networks. On the other hand, we develop two novel distillation modules, namely Depth-Aware Selective Feature Distillation (DASFD) and Depth-Aware Selective Relation Distillation (DASRD), which selectively learn positive features and relationships of objects by integrating depth uncertainty into feature and relation distillations, respectively. Our approach can be seamlessly integrated into various CNN-based and DETR-based models, where we take three recent models on KITTI and a recent model on NuScenes for validation. Extensive experiments show that our approach considerably improves the accuracy of the base models and thereby achieves the best accuracy compared with all recently released SOTA models.