LiDAR-Anchored Collaborative Distillation for Robust 2D Representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910021048074240 |
|---|---|
| author | Jo, Wonjun Ha, Hyunwoo Ji-Yeon, Kim Jeong, Hawook Oh, Tae-Hyun |
| author_facet | Jo, Wonjun Ha, Hyunwoo Ji-Yeon, Kim Jeong, Hawook Oh, Tae-Hyun |
| contents | As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems. Nevertheless, pre-trained 2D image encoders fall short in conducting the task under noisy and adverse weather conditions beyond clear daytime scenes, which require for robust visual perception. To address these issues, we propose a novel self-supervised approach, \textbf{Collaborative Distillation}, which leverages 3D LiDAR as self-supervision to improve robustness to noisy and adverse weather conditions in 2D image encoders while retaining their original capabilities. Our method outperforms competing methods in various downstream tasks across diverse conditions and exhibits strong generalization ability. In addition, our method also improves 3D awareness stemming from LiDAR's characteristics. This advancement highlights our method's practicality and adaptability in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12524 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LiDAR-Anchored Collaborative Distillation for Robust 2D Representations Jo, Wonjun Ha, Hyunwoo Ji-Yeon, Kim Jeong, Hawook Oh, Tae-Hyun Computer Vision and Pattern Recognition As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems. Nevertheless, pre-trained 2D image encoders fall short in conducting the task under noisy and adverse weather conditions beyond clear daytime scenes, which require for robust visual perception. To address these issues, we propose a novel self-supervised approach, \textbf{Collaborative Distillation}, which leverages 3D LiDAR as self-supervision to improve robustness to noisy and adverse weather conditions in 2D image encoders while retaining their original capabilities. Our method outperforms competing methods in various downstream tasks across diverse conditions and exhibits strong generalization ability. In addition, our method also improves 3D awareness stemming from LiDAR's characteristics. This advancement highlights our method's practicality and adaptability in real-world scenarios. |
| title | LiDAR-Anchored Collaborative Distillation for Robust 2D Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.12524 |