当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A novel multi-loss-based deep adversarial network for handling challenging cases in semi-supervised image semantic segmentation
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-03-22 , DOI: 10.1016/j.patrec.2021.03.017
Wei Huang , Zhanfei Shao , Mingyuan Luo , Peng Zhang , Yufei Zha

Image semantic segmentation is popular in computer vision and pattern recognition, since the high-level semantic understanding of images can be effectively realized. Based on whether and to what extent the training data should be labeled, most image semantic segmentation methods can be categorized into fully-supervised learning-based methods, weakly-supervised learning-based methods, and semi-supervised learning-based methods. Among them, semi-supervised image semantic segmentation receives increasing popularity recently, because of its flexibility and convenience in requiring partial training data to be labeled. Although semi-supervised image semantic segmentation is promising, its state-of-the-arts haven’t obtained satisfactory performance when handling challenging cases, including poor illumination, small-sized targets, multi-targets with the same semantics, etc. To tackle the above dilemmas, a novel multi-loss-based deep adversarial network is proposed in this paper. Technically, the more robust WGAN-GP model is utilized as the backbone of the novel network, instead of the conventional GAN model. Moreover, multiple losses including the cross entropy loss, the edge detection loss, the adversarial loss, and the semi-supervised loss, are all incorporated during the novel network’s training. Experimental analyses based on challenging cases shortlisted from the Pascal VOC 2012 dataset and the Cityscapes dataset suggest that, the novel network is capable to outperform state-of-the-arts in semi-supervised image semantic segmentation.



中文翻译:

一种新颖的基于多损失的深度对抗网络,用于处理半监督图像语义分割中的挑战性案例

图像语义分割在计算机视觉和模式识别中很流行,因为可以有效地实现对图像的高级语义理解。根据是否应该标记训练数据以及在何种程度上应该标记训练数据,大多数图像语义分割方法可以分为基于完全监督的基于学习的方法,基于弱监督的基于学习的方法和基于半监督的基于学习的方法。其中,由于半监督图像语义分割的灵活性和便利性,要求对部分训练数据进行标记,因此近来受到越来越多的欢迎。尽管半监督图像语义分割是有前途的,但其最新技术在处理具有挑战性的情况(包括照明不佳,目标尺寸较小,为了解决上述难题,本文提出了一种新颖的基于多损失的深度对抗网络。从技术上讲,更健壮的WGAN-GP模型被用作新型网络的主干,而不是传统的GAN模型。此外,在新颖网络的训练期间,包括交叉熵损失,边缘检测损失,对抗损失和半监督损失在内的多种损失都被并入。根据从Pascal VOC 2012数据集和Cityscapes数据集入围的具有挑战性的案例进行的实验分析表明,该新型网络能够在半监督图像语义分割方面胜过最新技术。更加健壮的WGAN-GP模型被用作新型网络的主干,而不是传统的GAN模型。此外,在新颖网络的训练期间,包括交叉熵损失,边缘检测损失,对抗损失和半监督损失在内的多种损失都被并入。根据从Pascal VOC 2012数据集和Cityscapes数据集入围的具有挑战性的案例进行的实验分析表明,该新型网络能够在半监督图像语义分割方面胜过最新技术。更加健壮的WGAN-GP模型被用作新型网络的主干,而不是传统的GAN模型。此外,在新颖网络的训练期间,包括交叉熵损失,边缘检测损失,对抗损失和半监督损失在内的多种损失都被并入。根据从Pascal VOC 2012数据集和Cityscapes数据集入围的具有挑战性的案例进行的实验分析表明,该新型网络能够在半监督图像语义分割方面胜过最新技术。在小说网络的培训中全部纳入。根据从Pascal VOC 2012数据集和Cityscapes数据集入围的具有挑战性的案例进行的实验分析表明,该新型网络能够在半监督图像语义分割方面胜过最新技术。在小说网络的培训中全部纳入。根据从Pascal VOC 2012数据集和Cityscapes数据集入围的具有挑战性的案例进行的实验分析表明,该新型网络能够在半监督图像语义分割方面胜过最新技术。

更新日期:2021-04-02
down
wechat
bug