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 2104.04980cs.CV
收藏

3D点云对象及其他对象的零样本学习

Zero-Shot Learning on 3D Point Cloud Objects and Beyond

Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61);Australian National University(澳大利亚国立大学);North South University(南北大学);University of Oxford(牛津大学)

Ali Cheraghian, Shafinn Rahman, Townim F. Chowdhury, Dylan Campbell, Lars Petersson

摘要:

在二维图像分类的情况下,零样本学习,即学习识别在训练期间未看到的新类的任务,已经受到相当大的关注。然而,尽管3D传感器越来越普遍,但相应的3D点云分类问题尚未得到有意义的探索,并引入了新的挑战。在本文中,我们确定了一些挑战,并在3D域中应用2D零样本学习(ZML)方法来分析现有模型的性能。然后,我们提出了一种新的方法来解决特定于3D打印的问题。首先,我们提出了一个归纳的CNOL过程,然后将其扩展到三维点云分类的转换CNOL和广义CNOL(GNOL)设置。为此,开发了一种新颖的损失函数,其同时将可见语义与点云特征对准,并利用未标记的测试数据来解决一些已知问题(例如,领域自适应、中心和数据偏差的问题)。虽然设计的三维点云分类的特殊性,该方法也适用于更常见的使用情况下的二维图像分类。进行了一系列广泛的实验,在合成(ModelNet40,ModelNet10,McGill)和真实(ScanObjectNN)3D点云数据集上建立了最先进的GML和GML。

英文摘要:

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However, despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. In this paper, we identify some of the challenges and apply 2D Zero-Shot Learning (ZSL) methods in the 3D domain to analyze the performance of existing models. Then, we propose a novel approach to address the issues specific to 3D ZSL. We first present an inductive ZSL process and then extend it to the transductive ZSL and Generalized ZSL (GZSL) settings for 3D point cloud classification. To this end, a novel loss function is developed that simultaneously aligns seen semantics with point cloud features and takes advantage of unlabeled test data to address some known issues (e.g., the problems of domain adaptation, hubness, and data bias). While designed for the particularities of 3D point cloud classification, the method is shown to also be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL on synthetic (ModelNet40, ModelNet10, McGill) and real (ScanObjectNN) 3D point cloud datasets.

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。

↑