Combine Supervised Edge and Semantic Supplement for Instance Segmentation

Abstract

Two-stage instance segmentation method outperforms the one-stage counterpart on complex occasions. However, we found that the RoIAlign operation identifies the feature map to smaller size, and the convolution or up-sampling causes the loss of detailed information. All these make it difficult to achieve precise segmentation. To circumvent the issue, we propose a simple and efficient anchor-free model for instance segmentation. We name it as CSAS because it combines the detection-based and segmentation-based idea. The CSAS adopts the two-stage paradigm, which mainly includes detection and segmentation. The box head not only considers the location accuracy into confidence score but calculates the IoU loss of regression, which leads to a gain of 1.5%. The mask head adopts the multi-task learning to accomplish precise segmentation, and it grows 1.7 points. Using the ResNet-50-FPN, a single CSAS obtains 1.6% improvement over the Mask R-CNN. Our result demonstrates that CSAS is capable of gaining the complete mask of instance. We conclude that the detailed feature information is essential for precise segmentation, the idea is available for other segmentation tasks.

Keywords

• Instance segmentation
• multi-task learning
• anchor-free model
• instance boundary