论文标题
通过学习注释一致实例进行弱监督的实例细分
Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances
论文作者
论文摘要
弱监督实例细分的最新方法取决于两个组成部分：（i）伪标签生成模型，该模型提供了与给定注释一致的实例； （ii）实例分割模型，该模型以监督方式训练，使用伪标签作为地面真相。与以前的方法不同，我们使用条件分布明确地对伪标签生成过程中的不确定性进行了建模。从我们条件分布中得出的样本可提供准确的伪标签，这是由于使用语义类别的一单位术语，边界意识到的成对平滑度术语和注释意识到高阶术语。此外，我们将实例分割模型表示为注释不可知的预测分布。与以前的方法相反，我们的表示使我们能够定义一个关节概率学习目标，以最大程度地减少两个分布之间的差异。我们的方法在Pascal VOC 2012数据集上实现了最新的结果，表现优于最佳基线m [email protected]和4.8％[email protected]。
Recent approaches for weakly supervised instance segmentations depend on two components: (i) a pseudo label generation model that provides instances which are consistent with a given annotation; and (ii) an instance segmentation model, which is trained in a supervised manner using the pseudo labels as ground-truth. Unlike previous approaches, we explicitly model the uncertainty in the pseudo label generation process using a conditional distribution. The samples drawn from our conditional distribution provide accurate pseudo labels due to the use of semantic class aware unary terms, boundary aware pairwise smoothness terms, and annotation aware higher order terms. Furthermore, we represent the instance segmentation model as an annotation agnostic prediction distribution. In contrast to previous methods, our representation allows us to define a joint probabilistic learning objective that minimizes the dissimilarity between the two distributions. Our approach achieves state of the art results on the PASCAL VOC 2012 data set, outperforming the best baseline by 4.2% [email protected] and 4.8% [email protected].
