SAIS: Single-stage Anchor-free Instance Segmentation
This addresses instance segmentation for computer vision applications, offering an efficient alternative to existing methods.
The paper tackles instance segmentation by proposing SAIS, a single-stage anchor-free method that predicts mask coefficients and prototypes, then combines them to generate masks, achieving state-of-the-art performance on MS COCO with reduced memory usage.
In this paper, we propose a simple yet efficientinstance segmentation approach based on the single-stage anchor-free detector, termed SAIS. In our approach, the instancesegmentation task consists of two parallel subtasks which re-spectively predict the mask coefficients and the mask prototypes.Then, instance masks are generated by linearly combining theprototypes with the mask coefficients. To enhance the quality ofinstance mask, the information from regression and classificationis fused to predict the mask coefficients. In addition, center-aware target is designed to preserve the center coordination ofeach instance, which achieves a stable improvement in instancesegmentation. The experiment on MS COCO shows that SAISachieves the performance of the exiting state-of-the-art single-stage methods with a much less memory footpr