Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic segmentation results over a small set of pixel-level mask annotations and a large set of box annotations. The basic idea is exploring detection models to simplify the pixel-level supervised learning task and thus reduce the required amount of mask annotations. Our architecture, named DASNet, consists of three modules: detection, attention, and segmentation. The detection module detects all classes of objects, the attention module generates multi-scale class-specific features, and the segmentation module recovers the binary masks. Our method demonstrates substantially improved performance compared to existing semi-supervised approaches on PASCAL VOC 2012 dataset.