arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1903.08773cs.CV
收藏

鲁棒图像分割质量评价

Robust Image Segmentation Quality Assessment

University of Iowa(爱荷华大学)

Leixin Zhou, Wenxiang Deng, Xiaodong Wu

摘要:

基于深度学习的图像分割方法已经取得了巨大的成功,在某些应用中甚至具有人类水平的准确性。然而,由于深度学习的黑箱性质,最好的方法在某些情况下可能会失败。因此,预测分割质量没有地面真相将是非常重要的,特别是在临床实践中。近年来,人们提出通过训练神经网络来回归估计质量得分。虽然它可以实现有前途的预测精度,网络遭受鲁棒性问题,例如,它是容易受到对抗攻击。在本文中,我们建议利用输入图像和重建图像之间的差异来缓解这个问题,这是以待评估的分割为条件的,以降低从原始输入图像过拟合到不期望的图像特征的机会,从而提高鲁棒性。在ACDC17数据集上的实验结果表明,该方法是可行的。

英文摘要:

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus predicting segmentation quality without ground truth would be very crucial especially in clinical practice. Recently, people proposed to train neural networks to estimate the quality score by regression. Although it can achieve promising prediction accuracy, the network suffers robustness problem, e.g. it is vulnerable to adversarial attacks. In this paper, we propose to alleviate this problem by utilizing the difference between the input image and the reconstructed image, which is conditioned on the segmentation to be assessed, to lower the chance to overfit to the undesired image features from the original input image, and thus to increase the robustness. Results on ACDC17 dataset demonstrated our method is promising.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑