利用可分离卷积和多级特征的实例分割

实例分割是一项具有挑战性的任务，它不仅需要每个实例的边界框，而且需要精确的像素级分割掩码.最近提出的端到端的全卷积实例感知分割网络（FCIS）在检测与分割的结合方面做得很好.但是，FCIS没有利用低层特征，而低层次的特征信息在检测和分割上都证明是有用的.在FCIS的基础上，提出了一种新的模型，充分利用了各层次的特征，并对实例分割模块进行了优化.该方法在检测分支中使用了具有大型卷积核的可分离卷积来获得更精确的边界框.同时，设计了一个包含边界细化操作的分割模块，以获得更精确的掩模.此外，将Resnet-101网络中的低级、中级和高级特征组合成4个不同级别的新特征，每个新特征都被用于生成实例的掩码.这些掩码被相加之后通过进一步细化以产生最终的最精确的掩模.通过这3项改进，实验结果表明，该方法明显优于基线方法FCIS，相比于FCIS，该方法在PASCAL VOC数据集上的评测指标mAP^r@0.5和mAP^r@0.7分别提高了4.9%和5.8%.

Instance Segmentation with Separable Convolutions and Multi-level Features

Instance segmentation is a challenging task for it requires not only bounding-box of each instance but also precise segmentation mask of it. Recently proposed fully convolutional instance-aware semantic segmentation (FCIS) has done a good job in combining detection and segmentation. But FCIS cannot make use of low level features, which is proved useful in both detection and segmentation. Based on FCIS, a new model is proposed which refines the instance masks with features of all levels. In the proposed method, large kernel separable convolutions are employed in the detection branch to get more accurate bounding-boxes. Simultaneously, a segmentation module containing boundary refinement operation is designed to get more precise masks. Moreover, the low level, medium level, and high level features in Resnet-101 are combined into new features of four different levels, each of which is employed to generate a mask of an instance. These masks are added and refined to produce the final most accurate one. With the three improvements, the proposed approach significantly outperforms baseline FCIS as it provides 4.9% increase in mAP^r@0.5 and 5.8% increase in mAP^r@0.7 on PASCAL VOC.