Boundary-preserving Mask R-CNN

2020/07/17 by Tianheng Cheng, Cheng, Tianheng, Xinggang Wang +5 · 5 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Object Detection Techniques #Infrastructure Maintenance and Monitoring #cs.CV

paper · pdf · doi:10.48550/arxiv.2007.08921

17 pages, 8 figures. Accepted by ECCV 2020

arxiv created 2020/07/17 · openalex publication_date 2020/07/17 · arxiv updated 2020/07/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object boundaries and shapes, leading coarse and indistinct mask prediction results and imprecise localization. To remedy these problems, we propose a conceptually simple yet effective Boundary-preserving Mask R-CNN (BMask R-CNN) to leverage object boundary information to improve mask localization accuracy. BMask R-CNN contains a boundary-preserving mask head in which object boundary and mask are mutually learned via feature fusion blocks. As a result, the predicted masks are better aligned with object boundaries. Without bells and whistles, BMask R-CNN outperforms Mask R-CNN by a considerable margin on the COCO dataset; in the Cityscapes dataset, there are more accurate boundary groundtruths available, so that BMask R-CNN obtains remarkable improvements over Mask R-CNN. Besides, it is not surprising to observe that BMask R-CNN obtains more obvious improvement when the evaluation criterion requires better localization (e.g., AP₇₅) as shown in Fig.1. Code and models are available at \urlhttps://github.com/hustvl/BMaskR-CNN.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• Deep High-Resolution Representation Learning for Visual Recognition
• Conditional Convolutions for Instance Segmentation

Cited by

• DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering
• Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter
• UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken
• Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation
• DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
• BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation

Related

• Faster Training of Mask R-CNN by Focusing on Instance Boundaries
• BshapeNet: Object Detection and Instance Segmentation with Bounding Shape Masks
• Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
• MaskPlus: Improving Mask Generation for Instance Segmentation
• LevelSet R-CNN: A Deep Variational Method for Instance Segmentation