CoDEPS：面向深度估计与全景分割的在线持续学习
CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation
AI总结：
针对机器人开放环境感知鲁棒性问题，提出在线持续学习方法CoDEPS，结合经验重放、域混合伪标签与高效重放缓冲采样策略，实现多域适配且缓解遗忘，性能达SOTA。
摘要：
在开放世界中运行的机器人需要对从未见过的环境具备高度鲁棒性。理想情况下，机器人能够在无需人类监督的情况下自行适应新条件，例如自动调整其感知系统以适应不断变化的光照条件。在本研究中，我们针对新环境下基于深度学习的单目深度估计与全景分割任务，开展在线式持续学习研究。我们提出了CoDEPS方法，用于执行涉及多个真实世界域的持续学习，同时通过利用经验重放机制缓解灾难性遗忘问题。具体而言，我们提出了一种新颖的域混合策略，用于生成伪标签以适配全景分割任务。此外，我们通过利用基于稀有语义类别采样和图像多样性构建固定大小重放缓冲区的采样策略，明确解决了机器人系统存储容量有限的问题。我们在多个真实世界数据集上对CoDEPS进行了广泛评估，结果表明该方法能够成功适配未见过的环境，同时不会牺牲在先前域上的性能，并且取得了当前最优的结果。本研究的代码已公开发布于http://codeps.cs.uni-freiburg.de。
英文摘要：
Operating a robot in the open world requires a high level of robustness with respect to previously unseen environments. Optimally, the robot is able to adapt by itself to new conditions without human supervision, e.g., automatically adjusting its perception system to changing lighting conditions. In this work, we address the task of continual learning for deep learning-based monocular depth estimation and panoptic segmentation in new environments in an online manner. We introduce CoDEPS to perform continual learning involving multiple real-world domains while mitigating catastrophic forgetting by leveraging experience replay. In particular, we propose a novel domain-mixing strategy to generate pseudo-labels to adapt panoptic segmentation. Furthermore, we explicitly address the limited storage capacity of robotic systems by leveraging sampling strategies for constructing a fixed-size replay buffer based on rare semantic class sampling and image diversity. We perform extensive evaluations of CoDEPS on various real-world datasets demonstrating that it successfully adapts to unseen environments without sacrificing performance on previous domains while achieving state-of-the-art results. The code of our work is publicly available at http://codeps.cs.uni-freiburg.de.
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。
