mlsanityData to 7 Oct 2026

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

arXiv 2104.05239 ↗First posted 12 Apr 2021cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundary-aware metrics. Moreover, by applying the BPR framework to the PolyTransform + SegFix baseline, we reached 1st place on the Cityscapes leaderboard.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 51 of its 56 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

51 of 56 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
38 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  4. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  5. 2019Objects as Pointscited by 1,172
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  7. 2018Path Aggregation Network for Instance Segmentationcited by 796
  8. 2017Focal Loss for Dense Object Detectioncited by 749
  9. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  10. 2019Panoptic Feature Pyramid Networkscited by 644
  11. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  12. 2020ResNeSt: Split-Attention Networkscited by 445
  13. 2019YOLACT: Real-time Instance Segmentationcited by 441
  14. 2019PointRend: Image Segmentation as Renderingcited by 439
  15. 2020Conditional Convolutions for Instance Segmentationcited by 314
  16. 2019SOLO: Segmenting Objects by Locationscited by 289
  17. 2019Mask Scoring R-CNNcited by 265
  18. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  19. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  20. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  21. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 165
  22. 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
  23. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  24. 2020Deep Snake for Real-Time Instance Segmentationcited by 111
  25. 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
  26. 2020SegFix: Model-Agnostic Boundary Refinement for Segmentationcited by 97
  27. 2019PolyTransform: Deep Polygon Transformer for Instance Segmentationcited by 92
  28. 2019Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidthcited by 88
  29. 2016Deep Watershed Transform for Instance Segmentationcited by 77
  30. 2020Boundary-preserving Mask R-CNNcited by 74
  31. 2019AdaptIS: Adaptive Instance Selection Networkcited by 64
  32. 2016InstanceCut: from Edges to Instances with MultiCutcited by 48
  33. 2020Mask Encoding for Single Shot Instance Segmentationcited by 47
  34. 2019Explicit Shape Encoding for Real-Time Instance Segmentationcited by 41
  35. 2020Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentationcited by 38
  36. 2020Scaling Wide Residual Networks for Panoptic Segmentationcited by 32
  37. 2015Iterative Instance Segmentationcited by 19
  38. 2019EmbedMask: Embedding Coupling for One-stage Instance Segmentationcited by 15

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 11; 2024: 7; 2025: 10; 2026: 1.

43 papers.

Sort:

By area:

  1. 2023Segment Anything in High Qualitycited by 373
  2. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  3. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  4. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  5. 2021Mask Transfiner for High-Quality Instance Segmentationcited by 64
  6. 2022Sparse Instance Activation for Real-Time Instance Segmentationcited by 63
  7. 2024MGMap: Mask-Guided Learning for Online Vectorized HD Map Constructioncited by 52
  8. 2023FastInst: A Simple Query-Based Model for Real-Time Instance Segmentationcited by 32
  9. 2022Video Mask Transfiner for High-Quality Video Instance Segmentationcited by 28
  10. 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 28
  11. 2022FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsamplingcited by 24
  12. 2025SAMRefiner: Taming Segment Anything Model for Universal Mask Refinementcited by 19
31 more
  1. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  2. 2022SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentationcited by 12
  3. 2022RF-Next: Efficient Receptive Field Search for Convolutional Neural Networkscited by 10
  4. 2022Visual Recognition by Requestcited by 10
  5. 2023Recurrent Generic Contour-based Instance Segmentation with Progressive Learningcited by 9
  6. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  7. 2023PatchDCT: Patch Refinement for High Quality Instance Segmentationcited by 8
  8. 2025Training-Free Dataset Pruning for Instance Segmentationcited by 7
  9. 2024Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imagingcited by 5
  10. 2024Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representationscited by 4
  11. 2025Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinementcited by 4
  12. 2022Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Speciescited by 3
  13. 2024FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architecturescited by 3
  14. 2025Cell Instance Segmentation: The Devil Is in the Boundariescited by 3
  15. 2023PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentationcited by 2
  16. 2024Open-World Panoptic Segmentationcited by 2
  17. 2025GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentationcited by 2
  18. 2025rNCA: Self-Repairing Segmentation Maskscited by 2
  19. 2021Multi-Object Tracking and Segmentation with a Space-Time Memory Networkcited by 1
  20. 2021Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological imagescited by 1
  21. 2023High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinementcited by 1
  22. 2025Channel-wise Motion Features for Efficient Motion Segmentationcited by 1
  23. 2025FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentationcited by 1
  24. 2026Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbationcited by 1
  25. 20225th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentationcited by 0
  26. 2022TransFiner: A Full-Scale Refinement Approach for Multiple Object Trackingcited by 0
  27. 2023HAISTA-NET: Human Assisted Instance Segmentation Through Attentioncited by 0
  28. 2023PnPNet: Pull-and-Push Networks for Volumetric Segmentation with Boundary Confusioncited by 0
  29. 2024Judging from Support-set: A New Way to Utilize Few-Shot Segmentation for Segmentation Refinement Processcited by 0
  30. 2025Interactive Instance Annotation with Siamese Networkscited by 0
  31. 2025Resource-efficient Automatic Refinement of Segmentations via Weak Supervision from Light Feedbackcited by 0