Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data

• URL: http://arxiv.org/abs/2301.07283v3
• Date: Mon, 4 Sep 2023 18:38:51 GMT
• Title: Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
• Authors: Andrej Janda, Brandon Wagstaff, Edwin G. Ng, and Jonathan Kelly
• Abstract summary: Self-supervised pre-training on unlabelled data is one way to reduce the amount of manual annotations needed. We combine image and point cloud modalities by first learning self-supervised image features and then using these features to train a 3D model. Our pre-training method only requires a single scan of a scene and can be applied to cases where localization information is unavailable.
• Score: 7.145862669763328
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly smaller and more challenging to annotate than their image-based counterparts. Self-supervised pre-training on unlabelled data is one way to reduce the amount of manual annotations needed. Previous work has focused on pre-training with point clouds exclusively. While useful, this approach often requires two or more registered views. In the present work, we combine image and point cloud modalities by first learning self-supervised image features and then using these features to train a 3D model. By incorporating image data, which is often included in many 3D datasets, our pre-training method only requires a single scan of a scene and can be applied to cases where localization information is unavailable. We demonstrate that our pre-training approach, despite using single scans, achieves comparable performance to other multi-scan, point cloud-only methods.

Related papers

• Shelf-Supervised Multi-Modal Pre-Training for 3D Object Detection [52.66283064389691]
  We propose a shelf-supervised approach for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. We show that image-based shelf-supervision is helpful for training LiDAR-only and multi-modal (RGB + LiDAR) detectors.
  arXiv  Detail & Related papers  (2024-06-14T15:21:57Z)
• PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds [18.840000859663153]
  We propose PRED, a novel image-assisted pre-training framework for outdoor point clouds. The main ingredient of our framework is a Birds-Eye-View (BEV) feature map conditioned semantic rendering. We further enhance our model's performance by incorporating point-wise masking with a high mask ratio.
  arXiv  Detail & Related papers  (2023-11-08T07:26:09Z)
• 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)
• Self-Supervised Pre-training of 3D Point Cloud Networks with Image Data [6.121574833847397]
  Self-supervised pre-training on large unlabelled datasets is one way to reduce the amount of manual annotations needed. In the present work, we combine image and point cloud modalities, by first learning self-supervised image features and then using these features to train a 3D model. By incorporating image data, which is often included in many 3D datasets, our pre-training method only requires a single scan of a scene.
  arXiv  Detail & Related papers  (2022-11-21T19:09:52Z)
• Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning [59.64695628433855]
  We propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images. Basically, we design a dual-branch network equipped with an active labeling strategy, to maximize the power of tiny parts of labels. Our method even outperforms the state-of-the-art fully supervised competitors with less than 1% actively selected annotations.
  arXiv  Detail & Related papers  (2022-09-16T07:59:04Z)
• Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation [17.27850877649498]
  We introduce a method for weakly supervised segmentation of 3D scenes that combines self-training and active learning. We demonstrate that our approach leads to an effective method that provides improvements in scene segmentation over previous works and baselines.
  arXiv  Detail & Related papers  (2022-09-15T06:00:25Z)
• Self-Supervised Pretraining for 2D Medical Image Segmentation [0.0]
  Self-supervised learning offers a way to lower the need for manually annotated data by pretraining models for a specific domain on unlabelled data. We find that self-supervised pretraining on natural images and target-domain-specific images leads to the fastest and most stable downstream convergence. In low-data scenarios, supervised ImageNet pretraining achieves the best accuracy, requiring less than 100 annotated samples to realise close to minimal error.
  arXiv  Detail & Related papers  (2022-09-01T09:25:22Z)
• P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting [94.11915008006483]
  We propose a novel Point-to-Pixel prompting for point cloud analysis. Our method attains 89.3% accuracy on the hardest setting of ScanObjectNN. Our framework also exhibits very competitive performance on ModelNet classification and ShapeNet Part Code.
  arXiv  Detail & Related papers  (2022-08-04T17:59:03Z)
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation [78.36781565047656]
  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.
  arXiv  Detail & Related papers  (2021-04-06T02:27:25Z)
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding [107.02479689909164]
  In this work, we aim at facilitating research on 3D representation learning. We measure the effect of unsupervised pre-training on a large source set of 3D scenes.
  arXiv  Detail & Related papers  (2020-07-21T17:59:22Z)

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.