对象边框标注数据的弱监督图像语义分割

针对图像语义分割应用中像素级标注数据费时昂贵的问题,主要研究以对象边框标注数据为代表的弱监督模型下的图像语义分割方法。使用基于金字塔的密集采样全卷积网络提取图像的像素级特征,并用GrabCut算法转化对弱监督数据进行数据标记,通过将图像特征和标记数据进行联合训练,构建了基于金字塔密集采样全卷积网络的对象边框标注弱监督图像语义分割模型,并在公开数据集上进行了验证。实验结果表明,所构建的弱监督模型与DET3-Proposed模型、全矩形转化模型以及Bbox-Seg模型相比,达到了更好的分割效果。

Image semantic segmentation of weakly supervised model with bounding box annotations data

For the pixel level marked data of image segmentation is time consuming and expensive, the image segmentation under the weak supervised model with bounding box annotations was studied. The high-resolution pixel features were extracted by a pyramid densely sampled fully convolution network, and then the weakly supervised data by the GrabCut algorithm was transformed. Finally, the image features and the labeled data were jointly trained. A model of weakly supervised image semantic segmentation based on fully convolution network was constructed and verified on public data set. Experiments show that the constructed weak supervised model has a better segmentation effect compared with DET3-Proposed model, expectation-maximization model and Bbox-Seg model.