arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.10130cs.LGcs.AIcs.CV
收藏

持续学习是否已准备好应对现实世界的挑战?

Is Continual Learning Ready for Real-world Challenges?

ETH Zurich(苏黎世联邦理工学院)

Theodora Kontogianni, Yuanwen Yue, Siyu Tang, Konrad Schindler

AI总结:

本文指出持续学习评估协议与现实挑战存在错位,提出新基准OCL-3DSS评估发现现有方法表现不佳,呼吁采用更贴近现实的实验协议以推动领域突破。

摘要:

尽管持续学习拥有悠久且成熟的学术历史,但其在现实世界场景中的应用仍然相当有限。本文认为,这种差距归因于持续学习的实际挑战与当前使用的评估协议之间的错位,使得提出的解决方案无法有效应对现实世界设置的复杂性。我们使用一个新的3D语义分割基准OCL-3DSS验证了我们的假设并评估了迄今为止的进展。我们通过利用更现实的协议调查了文献中的各种持续学习方案,这些协议需要针对动态、现实世界场景(例如,在机器人和3D视觉应用中)进行在线和持续学习。结果令人清醒:所有考虑的方法表现都很差,显著偏离了联合离线训练的上限。这引发了关于现有方法在现实环境中适用性的质疑。我们的论文旨在发起一场范式转变,提倡通过更好地模拟现实世界条件的新实验协议来采用持续学习方法,以促进该领域的突破。

英文摘要:

Despite continual learning's long and well-established academic history, its application in real-world scenarios remains rather limited. This paper contends that this gap is attributable to a misalignment between the actual challenges of continual learning and the evaluation protocols in use, rendering proposed solutions ineffective for addressing the complexities of real-world setups. We validate our hypothesis and assess progress to date, using a new 3D semantic segmentation benchmark, OCL-3DSS. We investigate various continual learning schemes from the literature by utilizing more realistic protocols that necessitate online and continual learning for dynamic, real-world scenarios (eg., in robotics and 3D vision applications). The outcomes are sobering: all considered methods perform poorly, significantly deviating from the upper bound of joint offline training. This raises questions about the applicability of existing methods in realistic settings. Our paper aims to initiate a paradigm shift, advocating for the adoption of continual learning methods through new experimental protocols that better emulate real-world conditions to facilitate breakthroughs in the field.

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。

↑