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 2003.00535cs.ROcs.CV
收藏

3DCFS:基于耦合特征选择的快速鲁棒三维语义-实例分割

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Fudan University(复旦大学);Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院上海微系统与信息技术研究所);Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University(复旦大学脑科学研究院);University of Warwick(华威大学)

Liang Du, Jingang Tan, Xiangyang Xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang

摘要:

我们提出了一种新的快速和强大的三维点云分割框架,通过耦合特征选择,命名为3DCFS,联合执行语义和实例分割。受人类场景感知过程的启发,我们设计了一个新的耦合特征选择模块,命名为CFSM,自适应地选择和融合的相互语义和实例功能,从两个任务在耦合的方式。为了进一步提高3DCFS中实例分割任务的性能,我们研究了一个损失函数,它可以帮助模型在训练过程中学习平衡输出嵌入维数的大小,这使得计算欧几里得距离更加可靠,并增强了模型的泛化能力。大量的实验表明,我们的3DCFS优于国家的最先进的方法在基准数据集的准确性,速度和计算成本。

英文摘要:

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost.

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。

↑