Mask Scoring R-CNN

  title={Mask Scoring R-CNN},
  author={Z. Huang and Lichao Huang and Yongchao Gong and C. Huang and Xinggang Wang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Z. Huang, Lichao Huang, +2 authors Xinggang Wang
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. [...] Key Method The proposed network block takes the instance feature and the corresponding predicted mask together to regress the mask IoU. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. By extensive evaluations on the COCO dataset, Mask…Expand Abstract
    140 Citations

    Figures, Tables, and Topics from this paper.

    Boundary-preserving Mask R-CNN
    • 4
    • PDF
    Dual-Supervised Instance Segmentation Network Combined with Priori Corner Information
    Supervised Edge Attention Network for Accurate Image Instance Segmentation
    Conditional Convolutions for Instance Segmentation
    • 9
    • PDF
    Mask Encoding for Single Shot Instance Segmentation
    • 6
    • PDF
    Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
    MU R-CNN: A Two-Dimensional Code Instance Segmentation Network Based on Deep Learning
    • 2
    • Highly Influenced
    • PDF
    Deep Variational Instance Segmentation
    Shape-aware Feature Extraction for Instance Segmentation
    • 2


    Instance-Sensitive Fully Convolutional Networks
    • 241
    • PDF
    Proposal-Free Network for Instance-Level Object Segmentation
    • 167
    • PDF
    Semantic Instance Segmentation with a Discriminative Loss Function
    • 191
    • PDF
    Instance-Aware Semantic Segmentation via Multi-task Network Cascades
    • Jifeng Dai, Kaiming He, Jian Sun
    • Computer Science
    • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2016
    • 758
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,919
    • PDF
    Segmentation-Aware Convolutional Networks Using Local Attention Masks
    • 68
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 19,562
    • Highly Influential
    • PDF
    Fully Convolutional Instance-Aware Semantic Segmentation
    • 471
    • PDF
    R-FCN: Object Detection via Region-based Fully Convolutional Networks
    • 2,671
    • PDF
    Learning to Segment Object Candidates
    • 526
    • PDF