mlsanityData to 7 Oct 2026

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

arXiv 1503.00848 ↗First posted 3 Mar 2015cs.CVcited by 90

Not on the map. Why?

Abstract (arXiv)

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object proposals by exploring efficiently their combinatorial space. We also present Single-scale Combinatorial Grouping (SCG), a faster version of MCG that produces competitive proposals in under five second per image. We conduct an extensive and comprehensive empirical validation on the BSDS500, SegVOC12, SBD, and COCO datasets, showing that MCG produces state-of-the-art contours, hierarchical regions, and object proposals.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 12; 2023: 20; 2024: 13; 2025: 11; 2026: 5.

90 papers.

Sort:

By area:

  1. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  2. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  3. 2024GARField: Group Anything with Radiance Fieldscited by 108
  4. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  5. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  6. 2021Pointly-Supervised Instance Segmentationcited by 83
  7. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  8. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  9. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  10. 2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
  11. 2022Box-supervised Instance Segmentation with Level Set Evolutioncited by 41
  12. 2022H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detectioncited by 36
38 more
  1. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  2. 2023Rotating Features for Object Discoverycited by 29
  3. 2023CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detectioncited by 28
  4. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  5. 2021GraphFPN: Graph Feature Pyramid Network for Object Detectioncited by 25
  6. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  7. 2022Box2Mask: Box-supervised Instance Segmentation via Level-set Evolutioncited by 22
  8. 2023Towards Unsupervised Object Detection From LiDAR Point Cloudscited by 22
  9. 2021Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Imagescited by 20
  10. 2023Mask-Free Video Instance Segmentationcited by 20
  11. 2021Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistencycited by 19
  12. 2021Bounding Box Tightness Prior for Weakly Supervised Image Segmentationcited by 19
  13. 2024Zero-Shot Object-Centric Representation Learningcited by 19
  14. 2021Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Miningcited by 15
  15. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  16. 2025CTRL-O: Language-Controllable Object-Centric Visual Representation Learningcited by 12
  17. 2022Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaborationcited by 11
  18. 2023SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentationcited by 11
  19. 2023Weakly Supervised Open-Vocabulary Object Detectioncited by 11
  20. 2024DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detectioncited by 11
  21. 2025Are We Done with Object-Centric Learning?cited by 10
  22. 2022Extending One-Stage Detection with Open-World Proposalscited by 9
  23. 2024WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognitioncited by 9
  24. 2021Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videoscited by 8
  25. 2021Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Predictioncited by 8
  26. 2023Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervisioncited by 8
  27. 2023Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Priorcited by 8
  28. 2024BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labelscited by 8
  29. 2023Cycle Consistency Driven Object Discoverycited by 7
  30. 2023Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Mapscited by 7
  31. 2022Multi-task Fusion for Efficient Panoptic-Part Segmentationcited by 6
  32. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  33. 2021Flip Learning: Erase to Segmentcited by 5
  34. 2024Complete Instances Mining for Weakly Supervised Instance Segmentationcited by 5
  35. 2021Superpixel-based Refinement for Object Proposal Generationcited by 4
  36. 2021Optimizing Edge Detection for Image Segmentation with Multicut Penaltiescited by 4
  37. 2023Perceptual Group Tokenizer: Building Perception with Iterative Groupingcited by 4
  38. 2024ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Modelcited by 4

50 most cited of 90 All 90 (JSON)