English

Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation

Computer Vision and Pattern Recognition 2021-10-20 v1

Abstract

This paper presents Mask-aware Intersection-over-Union (maIoU) for assigning anchor boxes as positives and negatives during training of instance segmentation methods. Unlike conventional IoU or its variants, which only considers the proximity of two boxes; maIoU consistently measures the proximity of an anchor box with not only a ground truth box but also its associated ground truth mask. Thus, additionally considering the mask, which, in fact, represents the shape of the object, maIoU enables a more accurate supervision during training. We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method. Using ATSS with maIoU consistently outperforms (i) ATSS with IoU by 1\sim 1 mask AP, (ii) baseline YOLACT with fixed IoU threshold assigner by 2\sim 2 mask AP over different image sizes and (iii) decreases the inference time by 25%25 \% owing to using less anchors. Then, exploiting this efficiency, we devise maYOLACT, a faster and +6+6 AP more accurate detector than YOLACT. Our best model achieves 37.737.7 mask AP at 2525 fps on COCO test-dev establishing a new state-of-the-art for real-time instance segmentation. Code is available at https://github.com/kemaloksuz/Mask-aware-IoU

Keywords

Cite

@article{arxiv.2110.09734,
  title  = {Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation},
  author = {Kemal Oksuz and Baris Can Cam and Fehmi Kahraman and Zeynep Sonat Baltaci and Sinan Kalkan and Emre Akbas},
  journal= {arXiv preprint arXiv:2110.09734},
  year   = {2021}
}

Comments

BMVC 2021, camera ready version

R2 v1 2026-06-24T06:59:46.744Z