paper-with-me

Papers

Weakly Supervised 3D Segmentation via Receptive-driven Pseudo Label Consistency and Structural Consistency

2023-06-26 · journal 2023 6 · Yuxiang Lan,Yachao Zhang,Yanyun Qu,Cong Wang,Chengyang Li,Jia Cai,Yuan Xie,Zongze Wu

As manual point-wise label is time and labor-intensive for fully supervised large-scale point cloud semantic segmentation, weakly supervised method is increasingly active. However, existing methods fail to generate high-quality pseudo labels effectively, leading to unsatisfactory results. In this paper, we propose a weakly supervised point cloud semantic segmentation framework via receptive-driven pseudo label consistency and structural consistency to mine potential knowledge. Specifically, we propose three consistency contrains: pseudo label consistency among different scales, semantic structure consistency between intra-class features and class-level relation structure consistency between pair-wise categories. Three consistency constraints are jointly used to effectively prepares and utilizes pseudo labels simultaneously for stable training. Finally, extensive experimental results on three challenging datasets demonstrate that our method significantly outperforms state-of-the-art weakly supervised methods and even achieves comparable performance to the fully supervised methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Pseudo LabelSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

WegFormer: Transformers for Weakly Supervised Semantic Segmentation

2022-03-16 · Chunmeng Liu, Enze Xie, Wenjia Wang, Wenhai Wang 외

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context informatio…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching

2024-07-18 · Xingyue Zhao, Peiqi Li, Xiangde Luo, Meng Yang 외

Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is b…

Pseudo LabelSegmentation

Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency

2023-09-18 · Meng Han, Xiangde Luo, Wenjun Liao, Shichuan Zhang 외

Multi-organ segmentation in abdominal Computed Tomography (CT) images is of great importance for diagnosis of abdominal lesions and subsequent treatment planning. Though deep learning based methods have attained high per…

Computed Tomography (CT)DecoderOrgan SegmentationSegmentation+1

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation

2021-08-30 · ICCV 2021 10 · Yi Li, Zhanghui Kuang, Liyang Liu, Yimin Chen 외

Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we …

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation

2018-03-07 · Tianyi Zhang, Guosheng Lin, Jianfei Cai, Tong Shen 외

Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other for…

Image CaptioningSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1