基于LiDAR的协同蒸馏用于鲁棒的2D表示
LiDAR-Anchored Collaborative Distillation for Robust 2D Representations
AI总结：
本文提出基于LiDAR的协同蒸馏方法，通过自监督提升2D图像编码器在恶劣天气下的鲁棒性，并增强3D感知能力。
摘要：
随着深度学习的不断发展，自监督学习取得了显著进展。它使2D图像编码器能够提取有用的特征，用于各种下游任务，包括与基于视觉系统相关的任务。然而，预训练的2D图像编码器在处理非清晰白天场景以外的嘈杂和恶劣天气条件下的任务时存在不足，这需要鲁棒的视觉感知。为了解决这些问题，我们提出了一种新的自监督方法，即协同蒸馏，利用3D LiDAR作为自监督，以提高2D图像编码器在嘈杂和恶劣天气条件下的鲁棒性，同时保留其原有能力。我们的方法在各种下游任务中优于竞争方法，在多样的条件下表现出强大的泛化能力。此外，我们的方法还提高了来自LiDAR特性的3D意识。这一进步突显了我们的方法在现实世界场景中的实用性和适应性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
