The weakly supervised instance segmentation is a challenging task. The existing methods typically use bounding boxes as supervision and optimize the network with a regularization loss term such as pairwise color affinity loss for instance segmentation. Through systematic analysis, we found that the commonly used pairwise affinity loss has two limitations: (1) it works with color affinity but leads to inferior performance with other modalities such as depth gradient, (2)the original affinity loss does not prevent trivial predictions as intended but actually accelerates this process due to the affinity loss term being symmetric. To overcome these two limitations, in this paper, we propose a novel asymmetric affinity loss which provides the penalty against the trivial prediction and generalizes well with affinity loss from different modalities. With the proposed asymmetric affinity loss, our method outperforms the state-of-the-art methods on the Cityscapes dataset and outperforms our baseline method by 3.5% in mask AP.
翻译:监管不力的例系分割是一项艰巨的任务。 现有方法通常使用捆绑框作为监管,优化网络,使用正规化损失术语,如双色近亲损失等。 通过系统分析,我们发现常用的对称亲近损失有两个局限性:(1) 它与颜色亲近有关,但导致与深度梯度等其他模式的性能较差,(2) 原始亲近损失并不防止本意的微小预测,但实际上加快了这一过程,因为亲近损失术语是对称的。为了克服这两个限制,我们在本文件中提出了新的不对称近亲损失,对微不足道的预测规定了惩罚,并概括了不同模式的亲近损失。由于拟议的不对称亲近性损失,我们的方法在市域数据集上超越了最先进的方法,在面具AP中比我们的基线方法高出3.5%。