arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08919cs.CV
收藏

VIPriors Challenge的边缘保持引导语义分割

Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge

National Pingtung University of Science and Technology(屏东科技大学)

Chih-Chung Hsu, Hsin-Ti Ma

摘要:

语义分割是计算机视觉中最具吸引力的研究领域之一。在VIPriors挑战中,仅允许非常有限数量的训练样本,导致当前最先进的基于深度学习的语义分割技术难以很好地训练。为了克服这个缺点,因此,我们提出了边缘保护的指导,以获得额外的先验信息,以避免在小规模的训练数据集下的过拟合。首先,将双通道卷积层连接到传统语义分割网络的最后一层。然后,通过Sobel操作从地面真值计算边缘图,然后连接硬阈值操作以指示像素是否是边缘。然后,采用二维交叉熵损失来计算预测的边缘图与其真实值之间的损失,称为边缘保持损失。通过这种方式,不同实例之间的边界的连续性可以通过所提出的边缘保持损失来强制。实验结果表明,与现有的语义分割方法相比,该方法在小规模训练集下具有良好的分割效果。

英文摘要:

Semantic segmentation is one of the most attractive research fields in computer vision. In the VIPriors challenge, only very limited numbers of training samples are allowed, leading to that the current state-of-the-art and deep learning-based semantic segmentation techniques are hard to train well. To overcome this shortcoming, therefore, we propose edge-preserving guidance to obtain the extra prior information, to avoid the overfitting under small-scale training dataset. First, a two-channeled convolutional layer is concatenated to the last layer of the conventional semantic segmentation network. Then, an edge map is calculated from the ground truth by Sobel operation and followed by concatenating a hard-thresholding operation to indicate whether the pixel is the edge or not. Then, the two-dimensional cross-entropy loss is adopted to calculate the loss between the predicted edge map and its ground truth, termed as an edge-preserving loss. In this way, the continuity of boundaries between different instances can be forced by the proposed edge-preserving loss. Experiments demonstrate that the proposed method can achieve excellent performance under small-scale training set, compared to state-of-the-art semantic segmentation techniques.

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。

↑