ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2110.09734
21
8

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

19 October 2021
Kemal Oksuz
Baris Can Cam
Fehmi Kahraman
Z. S. Baltaci
Sinan Kalkan
Emre Akbas
ArXivPDFHTML
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∼1 mask AP, (ii) baseline YOLACT with fixed IoU threshold assigner by ∼2\sim 2∼2 mask AP over different image sizes and (iii) decreases the inference time by 25%25 \%25% owing to using less anchors. Then, exploiting this efficiency, we devise maYOLACT, a faster and +6+6+6 AP more accurate detector than YOLACT. Our best model achieves 37.737.737.7 mask AP at 252525 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

View on arXiv
Comments on this paper