mlsanityData to 7 Oct 2026

Learning to Fuse Things and Stuff

arXiv 1812.01192 ↗First posted 4 Dec 2018cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 4; 2024: 3; 2025: 0; 2026: 2.

26 papers.

Sort:

By area:

  1. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  2. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  3. 2022CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentationcited by 60
  4. 2021Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Imagescited by 48
  5. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  6. 2021PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentationcited by 36
  7. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  8. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  9. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  10. 2022Interactive Image Synthesis with Panoptic Layout Generationcited by 17
  11. 2022PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentationcited by 14
  12. 2021Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approachcited by 10
14 more
  1. 2022Visual Recognition by Requestcited by 10
  2. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  3. 2021Panoptic Segmentation Forecastingcited by 7
  4. 2022Multi-task Fusion for Efficient Panoptic-Part Segmentationcited by 6
  5. 2021Flying Guide Dog: Walkable Path Discovery for the Visually Impaired Utilizing Drones and Transformer-based Semantic Segmentationcited by 5
  6. 2021Hierarchical Lov'asz Embeddings for Proposal-free Panoptic Segmentationcited by 4
  7. 2024MC-PanDA: Mask Confidence for Panoptic Domain Adaptationcited by 4
  8. 2023Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Imagescited by 3
  9. 2021SE-PSNet: Silhouette-based Enhancement Feature for Panoptic Segmentation Networkcited by 2
  10. 2023JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentationcited by 2
  11. 2024Resolving Inconsistent Semantics in Multi-Dataset Image Segmentationcited by 1
  12. 2024HyCTAS: Multi-Objective Hybrid Convolution-Transformer Architecture Search for Real-Time Image Segmentationcited by 0
  13. 2026MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentationcited by 0
  14. 2026MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentationcited by 0