Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

Abstract

We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images. Unlike most existing methods that require voxel-wise densely labeled training data, our weakly-supervised CIVA-Net is the first model that only needs image-level class labels as guidance to learn accurate volumetric segmentation. Our model learns from cross-image co-occurrence for integral region generation, and explores inter-voxel affinity relations to predict segmentation with accurate boundaries. We empirically validate our model on both simulated and real cryo-ET datasets. Our experiments show that CIVA-Net achieves comparable performance to the state-of-the-art models trained with stronger supervision.

Cite

Text

Zhu et al. "Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00283

Markdown

[Zhu et al. "Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/zhu2021iccv-weakly/) doi:10.1109/ICCV48922.2021.00283

BibTeX

@inproceedings{zhu2021iccv-weakly,
  title     = {{Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations}},
  author    = {Zhu, Xiaoyu and Chen, Jeffrey and Zeng, Xiangrui and Liang, Junwei and Li, Chengqi and Liu, Sinuo and Behpour, Sima and Xu, Min},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {2834-2844},
  doi       = {10.1109/ICCV48922.2021.00283},
  url       = {https://mlanthology.org/iccv/2021/zhu2021iccv-weakly/}
}