arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.09164cs.CV
收藏

点式Transformer

Point Transformer

University of Oxford(牛津大学);The University of Hong Kong(香港大学);The Chinese University of Hong Kong(香港中文大学);Intel Labs(英特尔实验室)

Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

摘要:

自注意网络已经彻底改变了自然语言处理,并在图像分析任务(如图像分类和目标检测)方面取得了令人印象深刻的进展。受此成功的启发,我们研究了自注意网络在3D点云处理中的应用。我们为点云设计了自注意层,并使用这些层来构建自注意网络,用于语义场景分割,对象部分分割和对象分类等任务。我们的Point Transformer设计改进了以前跨域和任务的工作。例如,在用于大规模语义场景分割的具有挑战性的S3DIS数据集上,Point Transformer在Area 5上达到了70.4%的mIoU,比最强的先验模型高出3.3个绝对百分点,并首次超过了70%的mIoU阈值。

英文摘要:

Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.

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。

↑