# Boundary-preserving Mask R-CNN

arXiv: https://arxiv.org/abs/2007.08921 · HTML: https://mlsanity.com/paper/2007.08921/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 30 of 74)

- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation](https://mlsanity.com/paper/2105.01839/) (2021)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [SOLQ: Segmenting Objects by Learning Queries](https://mlsanity.com/paper/2106.02351/) (2021)
- [Mask Transfiner for High-Quality Instance Segmentation](https://mlsanity.com/paper/2111.13673/) (2021)
- [Sparse Instance Activation for Real-Time Instance Segmentation](https://mlsanity.com/paper/2203.12827/) (2022)
- [MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2404.00876/) (2024)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features](https://mlsanity.com/paper/2104.08569/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [Box-supervised Instance Segmentation with Level Set Evolution](https://mlsanity.com/paper/2207.09055/) (2022)
- [Instance Neural Radiance Field](https://mlsanity.com/paper/2304.04395/) (2023)
- [Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation](https://mlsanity.com/paper/2204.04655/) (2022)
- [AdaptiveSAM: Towards Efficient Tuning of SAM for Surgical Scene Segmentation](https://mlsanity.com/paper/2308.03726/) (2023)
- [AISFormer: Amodal Instance Segmentation with Transformer](https://mlsanity.com/paper/2210.06323/) (2022)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments](https://mlsanity.com/paper/2211.16200/) (2022)
- [FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation](https://mlsanity.com/paper/2303.08594/) (2023)
- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)
- [Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution](https://mlsanity.com/paper/2212.01579/) (2022)
- [Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?](https://mlsanity.com/paper/2203.13427/) (2022)
- [ContrastMask: Contrastive Learning to Segment Every Thing](https://mlsanity.com/paper/2203.09775/) (2022)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [AIParsing: Anchor-free Instance-level Human Parsing](https://mlsanity.com/paper/2207.06854/) (2022)
- [SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation](https://mlsanity.com/paper/2203.13312/) (2022)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)

## Abstract (arXiv)

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.