Inter Extreme Points Geodesics for Weakly Supervised Segmentation

• URL: http://arxiv.org/abs/2107.00583v1
• Date: Thu, 1 Jul 2021 16:16:50 GMT
• Title: Inter Extreme Points Geodesics for Weakly Supervised Segmentation
• Authors: Reuben Dorent, Samuel Joutard, Jonathan Shapey, Aaron Kujawa, Marc Modat, Sebastien Ourselin, Tom Vercauteren
• Abstract summary: $textitInExtremIS$ is a weakly supervised 3D approach to train a deep image segmentation network. Our fully-automatic method is trained end-to-end and does not require any test-time annotations.
• Score: 2.5772212255258777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce $\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of "annotated" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a Conditional Random Field formulation is used to encourage prediction consistency over homogeneous regions. Extensive experiments are performed on a large open dataset for Vestibular Schwannoma segmentation. $\textit{InExtremIS}$ obtained competitive performance, approaching full supervision and outperforming significantly other weakly supervised techniques based on bounding boxes. Moreover, given a fixed annotation time budget, $\textit{InExtremIS}$ outperforms full supervision. Our code and data are available online.

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)
• Temporal Action Localization with Enhanced Instant Discriminability [66.76095239972094]
  Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. We propose a one-stage framework named TriDet to resolve imprecise predictions of action boundaries by existing methods. Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets.
  arXiv  Detail & Related papers  (2023-09-11T16:17:50Z)
• 3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks [26.29122638813974]
  We propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.
  arXiv  Detail & Related papers  (2023-07-30T15:26:17Z)
• Constraint and Union for Partially-Supervised Temporal Sentence Grounding [70.70385299135916]
  temporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos. The existing fully-supervised setting achieves great performance but requires expensive annotation costs. This paper introduces an intermediate partially-supervised setting, i.e., only short-clip or even single-frame labels are available during training.
  arXiv  Detail & Related papers  (2023-02-20T09:14:41Z)
• Exploring Active 3D Object Detection from a Generalization Perspective [58.597942380989245]
  Uncertainty-based active learning policies fail to balance the trade-off between point cloud informativeness and box-level annotation costs. We propose textscCrb, which hierarchically filters out the point clouds of redundant 3D bounding box labels. Experiments show that the proposed approach outperforms existing active learning strategies.
  arXiv  Detail & Related papers  (2023-01-23T02:43:03Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining [17.69745159912481]
  We introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. Our method can achieve competitive performance compared with the recent fully-supervised methods.
  arXiv  Detail & Related papers  (2021-11-30T08:40:40Z)
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation [86.44301443789763]
  We propose Affinity Attention Graph Neural Network ($A2$GNN) for weakly supervised semantic segmentation. Our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets.
  arXiv  Detail & Related papers  (2021-06-08T02:19:21Z)
• Polygon-free: Unconstrained Scene Text Detection with Box Annotations [39.74109294551322]
  This study proposes an unconstrained text detection system termed Polygon-free (PF) PF is trained with only upright bounding box annotations. Experiments demonstrate that PF can combine general detectors to yield surprisingly high-quality pixel-level results.
  arXiv  Detail & Related papers  (2020-11-26T14:19:33Z)
• Salient Instance Segmentation with Region and Box-level Annotations [3.1458035003538884]
  New generation of saliency detection provides strong theoretical and technical basis for video surveillance. Due to the limited scale of the existing dataset and the high mask annotations cost, plenty of supervision source is urgently needed to train a well-performing salient instance model. We propose a novel salient instance segmentation framework by an inexact supervision without resorting to laborious labeling.
  arXiv  Detail & Related papers  (2020-08-19T03:43:45Z)

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.