One Thing One Click: A Self-Training Approach for Weakly Supervised 3D
Semantic Segmentation
- URL: http://arxiv.org/abs/2104.02246v2
- Date: Wed, 7 Apr 2021 05:58:22 GMT
- Title: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D
Semantic Segmentation
- Authors: Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu
- Abstract summary: We propose "One Thing One Click," meaning that the annotator only needs to label one point per object.
We iteratively conduct the training and label propagation, facilitated by a graph propagation module.
Our results are also comparable to those of the fully supervised counterparts.
- Score: 78.36781565047656
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point cloud semantic segmentation often requires largescale annotated
training data, but clearly, point-wise labels are too tedious to prepare. While
some recent methods propose to train a 3D network with small percentages of
point labels, we take the approach to an extreme and propose "One Thing One
Click," meaning that the annotator only needs to label one point per object. To
leverage these extremely sparse labels in network training, we design a novel
self-training approach, in which we iteratively conduct the training and label
propagation, facilitated by a graph propagation module. Also, we adopt a
relation network to generate per-category prototype and explicitly model the
similarity among graph nodes to generate pseudo labels to guide the iterative
training. Experimental results on both ScanNet-v2 and S3DIS show that our
self-training approach, with extremely-sparse annotations, outperforms all
existing weakly supervised methods for 3D semantic segmentation by a large
margin, and our results are also comparable to those of the fully supervised
counterparts.
Related papers
- Bayesian Self-Training for Semi-Supervised 3D Segmentation [59.544558398992386]
3D segmentation is a core problem in computer vision.
densely labeling 3D point clouds to employ fully-supervised training remains too labor intensive and expensive.
Semi-supervised training provides a more practical alternative, where only a small set of labeled data is given, accompanied by a larger unlabeled set.
arXiv Detail & Related papers (2024-09-12T14:54:31Z) - Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation [50.51125319374404]
We propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data.
Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches.
arXiv Detail & Related papers (2024-06-24T16:35:58Z) - Weakly Supervised 3D Instance Segmentation without Instance-level
Annotations [57.615325809883636]
3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data.
We propose the first weakly-supervised 3D instance segmentation method that only requires categorical semantic labels as supervision.
By generating pseudo instance labels from categorical semantic labels, our designed approach can also assist existing methods for learning 3D instance segmentation at reduced annotation cost.
arXiv Detail & Related papers (2023-08-03T12:30:52Z) - ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations [29.231508413247457]
3D instance segmentation methods often require fully-annotated dense labels for training.
We present ClickSeg, a novel click-level weakly supervised 3D instance segmentation method.
ClickSeg achieves $sim$90% of the accuracy of the fully-supervised counterpart.
arXiv Detail & Related papers (2023-07-19T02:49:44Z) - You Only Need One Thing One Click: Self-Training for Weakly Supervised
3D Scene Understanding [107.06117227661204]
We propose One Thing One Click'', meaning that the annotator only needs to label one point per object.
We iteratively conduct the training and label propagation, facilitated by a graph propagation module.
Our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy.
arXiv Detail & Related papers (2023-03-26T13:57:00Z) - Collaborative Propagation on Multiple Instance Graphs for 3D Instance
Segmentation with Single-point Supervision [63.429704654271475]
We propose a novel weakly supervised method RWSeg that only requires labeling one object with one point.
With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information.
Specifically, we propose a Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs.
arXiv Detail & Related papers (2022-08-10T02:14:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.