arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.07392cs.CV
收藏

3D现实世界挑战的联合监督和自监督学习

Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

Politecnico di Torino(都灵理工大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)

Antonio Alliegro, Davide Boscaini, Tatiana Tommasi

摘要:

点云处理和3D形状理解是非常具有挑战性的任务,其中深度学习技术已经显示出巨大的潜力。更进一步的进展对于允许人工智能代理与现实世界进行交互至关重要,其中注释数据的数量可能是有限的,并且整合新的知识来源对于支持自主学习至关重要。在这里,我们考虑了几种可能的场景,涉及合成和真实世界的点云,其中监督学习由于数据稀缺和大的域差距而失败。我们建议通过多任务模型利用自我监督来丰富标准特征表示,该模型可以解决3D难题,同时学习形状分类或零件分割的主要任务。一个广泛的分析调查Few-Shot,迁移学习和跨域设置显示了我们的方法的有效性与国家的最先进的3D形状分类和部分分割的结果。

英文摘要:

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact with the real world, where the amount of annotated data may be limited and integrating new sources of knowledge becomes crucial to support autonomous learning. Here we consider several possible scenarios involving synthetic and real-world point clouds where supervised learning fails due to data scarcity and large domain gaps. We propose to enrich standard feature representations by leveraging self-supervision through a multi-task model that can solve a 3D puzzle while learning the main task of shape classification or part segmentation. An extensive analysis investigating few-shot, transfer learning and cross-domain settings shows the effectiveness of our approach with state-of-the-art results for 3D shape classification and part segmentation.

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。

↑