An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation

Cheng Kun Yang, Ji Jia Wu, Kai Syun Chen, Yung Yu Chuang, Yen Yu Lin

研究成果: Conference contribution同行評審

30 引文 斯高帕斯(Scopus)

摘要

We address weakly supervised point cloud segmentation by proposing a new model, MIL-derived transformer, to mine additional supervisory signals. First, the transformer model is derived based on multiple instance learning (MIL) to explore pair-wise cloud-level supervision, where two clouds of the same category yield a positive bag while two of different classes produce a negative bag. It leverages not only individual cloud annotations but also pair-wise cloud semantics for model optimization. Second, Adaptive global weighted pooling (AdaGWP) is integrated into our transformer model to replace max pooling and average pooling. It introduces learnable weights to re-scale logits in the class activation maps. It is more robust to noise while discovering more complete foreground points under weak supervision. Third, we perform point subsampling and enforce feature equivariance between the original and subsampled point clouds for regularization. The proposed method is end-to-end trainable and is general because it can work with different backbones with diverse types of weak supervision signals, including sparsely annotated points and cloud-level labels. The experiments show that it achieves state-of-the-art performance on the S3DIS and ScanNet benchmarks. The source code will be available at https://github.com/jimmy15923/wspss_mil_transformer.

原文English
主出版物標題Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
發行者IEEE Computer Society
頁面11820-11829
頁數10
ISBN(電子)9781665469463
DOIs
出版狀態Published - 2022
事件2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States
持續時間: 19 6月 202224 6月 2022

出版系列

名字Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2022-June
ISSN(列印)1063-6919

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
國家/地區United States
城市New Orleans
期間19/06/2224/06/22

指紋

深入研究「An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation」主題。共同形成了獨特的指紋。

引用此