Corpus ID: 237605544

Mixed-supervised segmentation: Confidence maximization helps knowledge distillation

@article{Liu2021MixedsupervisedSC,
  title={Mixed-supervised segmentation: Confidence maximization helps knowledge distillation},
  author={Bingyuan Liu and Christian Desrosiers and Ismail Ben Ayed and Jos{\'e} Dolz},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.10902}
}
Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks (DNNs) require large training datasets with pixel-wise annotations. Obtaining these curated datasets is a cumbersome process which limits the applicability of DNNs in scenarios where annotated images are scarce. Mixed supervision is an appealing alternative for mitigating this obstacle. In this setting, only a small fraction of the data contains complete pixel-wise annotations and other… Expand

References

SHOWING 1-10 OF 72 REFERENCES
Teach me to segment with mixed supervision: Confident students become masters
TLDR
This work proposes a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the lower branch, and shows that the branch trained with reduced supervision largely outperforms the teacher. Expand
Mixed-Supervised Dual-Network for Medical Image Segmentation
TLDR
This paper proposes Mixed-Supervised Dual-Network (MSDN), a novel architecture which consists of two separate networks for the detection and segmentation tasks respectively, and a series of connection modules between the layers of the two networks. Expand
Annotation-cost Minimization for Medical Image Segmentation using Suggestive Mixed Supervision Fully Convolutional Networks
TLDR
A budget-based cost-minimization framework in a mixed-supervision setting via dense segmentations, bounding boxes, and landmarks is presented and a linear programming (LP) formulation combined with uncertainty and similarity based ranking strategy to judiciously select samples to be annotated next for optimal performance. Expand
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
TLDR
A novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images that can effectively leverage the unlabeled data by encouraging consistent predictions of the same input under different perturbations. Expand
Mutual information deep regularization for semi-supervised segmentation
TLDR
Experimental results show the proposed clustering loss based on mutual information that explicitly enforces prediction consistency between nearby pixels in unlabeled images, and for random perturbation of these images, to outperform recently-proposed approaches for semi-supervised and yield a performance comparable to fully-super supervised training. Expand
Semi-supervised Medical Image Segmentation via Learning Consistency Under Transformations
TLDR
A novel semi-supervised method that, in addition to supervised learning on labeled training images, learns to predict segmentations consistent under a given class of transformations on both labeled and unlabeled images. Expand
Constrained‐CNN losses for weakly supervised segmentation☆
TLDR
A differentiable penalty is proposed, which enforces inequality constraints directly in the loss function, avoiding expensive Lagrangian dual iterates and proposal generation and has the potential to close the gap between weakly and fully supervised learning in semantic medical image segmentation. Expand
Curriculum semi-supervised segmentation
TLDR
This study investigates a curriculum-style strategy for semi-supervised CNN segmentation, which devises a regression network to learn image-level information such as the size of a target region, and achieves very competitive results, approaching the performance of full-supervision. Expand
Semi-Supervised and Task-Driven Data Augmentation
TLDR
A novel task-driven data augmentation method where to synthesize new training examples, a generative network explicitly models and applies deformation fields and additive intensity masks on existing labelled data, modeling shape and intensity variations, respectively. Expand
ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Image Segmentation
  • Xinyue Huo, Lingxi Xie, +4 authors Qi Tian
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
The Asynchronous Teacher-Student Optimization (ATSO) algorithm is proposed, which breaks up continual learning from teacher to student and partitions the unlabeled training data into two subsets and alternately uses one subset to fine-tune the model which updates the labels on the other. Expand
...
1
2
3
4
5
...