mlsanityData to 7 Oct 2026

Weakly- and Semi-Supervised Panoptic Segmentation

arXiv 1808.03575 ↗First posted 10 Aug 2018cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks. In contrast to many popular instance segmentation approaches based on object detectors, our method does not predict any overlapping instances. Moreover, we are able to segment both "thing" and "stuff" classes, and thus explain all the pixels in the image. "Thing" classes are weakly-supervised with bounding boxes, and "stuff" with image-level tags. We obtain state-of-the-art results on Pascal VOC, for both full and weak supervision (which achieves about 95% of fully-supervised performance). Furthermore, we present the first weakly-supervised results on Cityscapes for both semantic- and instance-segmentation. Finally, we use our weakly supervised framework to analyse the relationship between annotation quality and predictive performance, which is of interest to dataset creators.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 9; 2023: 7; 2024: 3; 2025: 3; 2026: 1.

40 papers.

Sort:

By area:

  1. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  2. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  3. 2021Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Imagescited by 48
  4. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  5. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  6. 2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 37
  7. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  8. 2023DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Modelcited by 30
  9. 2021Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentationcited by 24
  10. 2023Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transportcited by 23
  11. 2022Pointly-Supervised Panoptic Segmentationcited by 20
  12. 2021Instance and Panoptic Segmentation Using Conditional Convolutionscited by 19
28 more
  1. 2021Panoptic Segmentation: A Reviewcited by 18
  2. 2021Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentationcited by 15
  3. 2021Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddingscited by 10
  4. 2021Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approachcited by 10
  5. 2021Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentationcited by 9
  6. 2022Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentationcited by 9
  7. 2022Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentationcited by 9
  8. 2022Multi-task Fusion for Efficient Panoptic-Part Segmentationcited by 6
  9. 2023Cyclic Learning: Bridging Image-level Labels and Nuclei Instance Segmentationcited by 5
  10. 2021Hierarchical Lov'asz Embeddings for Proposal-free Panoptic Segmentationcited by 4
  11. 2024Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detectioncited by 3
  12. 2025TRACE: Your Diffusion Model is Secretly an Instance Edge Detectorcited by 3
  13. 2025DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentationcited by 3
  14. 2021Weakly Supervised Multi-Object Tracking and Segmentationcited by 2
  15. 2023Training Semantic Segmentation on Heterogeneous Datasetscited by 2
  16. 2023JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentationcited by 2
  17. 2024MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentationcited by 2
  18. 2021Visual Boundary Knowledge Translation for Foreground Segmentationcited by 1
  19. 2021Simpler Does It: Generating Semantic Labels with Objectness Guidancecited by 1
  20. 2022ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particlescited by 1
  21. 2023ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical Imagescited by 1
  22. 2023Towards Omni-supervised Referring Expression Segmentationcited by 1
  23. 2024MLMT-CNN for Object Detection and Segmentation in Multi-layer and Multi-spectral Imagescited by 1
  24. 2022Learning with Weak Annotations for Robust Maritime Obstacle Detectioncited by 0
  25. 2022WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labelscited by 0
  26. 2022Connectivity-constrained Interactive Panoptic Segmentationcited by 0
  27. 2025Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Taskscited by 0
  28. 2026Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETRcited by 0