mlsanityData to 7 Oct 2026

Part-aware Panoptic Segmentation

arXiv 2106.06351 ↗First posted 11 Jun 2021cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing. For this novel task, we provide consistent annotations on two commonly used datasets: Cityscapes and Pascal VOC. Moreover, we present a single metric to evaluate PPS, called Part-aware Panoptic Quality (PartPQ). For this new task, using the metric and annotations, we set multiple baselines by merging results of existing state-of-the-art methods for panoptic segmentation and part segmentation. Finally, we conduct several experiments that evaluate the importance of the different levels of abstraction in this single task.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 11 Jun 2021.

Builds on

44 of 62 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2018Panoptic Segmentationcited by 796
  11. 2019Panoptic Feature Pyramid Networkscited by 644
  12. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
32 more
  1. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  2. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  3. 2020ResNeSt: Split-Attention Networkscited by 445
  4. 2019Panoptic-DeepLabcited by 362
  5. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  6. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  7. 2019Self-Correction for Human Parsingcited by 179
  8. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  9. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  10. 2019Seamless Scene Segmentationcited by 112
  11. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  12. 2019PolyTransform: Deep Polygon Transformer for Instance Segmentationcited by 92
  13. 2019Graphonomy: Universal Human Parsing via Graph Transfer Learningcited by 81
  14. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  15. 2018Attention-guided Unified Network for Panoptic Segmentationcited by 71
  16. 2018Devil in the Details: Towards Accurate Single and Multiple Human Parsingcited by 64
  17. 2019DeeperLab: Single-Shot Image Parsercited by 63
  18. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  19. 2018Parsing R-CNN for Instance-Level Human Analysiscited by 53
  20. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  21. 2016Semantic Object Parsing with Graph LSTMcited by 44
  22. 2020Unifying Training and Inference for Panoptic Segmentationcited by 37
  23. 2019Face Parsing with RoI Tanh-Warpingcited by 33
  24. 2019Real-Time Panoptic Segmentation from Dense Detectionscited by 31
  25. 2019Learning Instance Occlusion for Panoptic Segmentationcited by 30
  26. 2019SOGNet: Scene Overlap Graph Network for Panoptic Segmentationcited by 26
  27. 2020GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wildcited by 25
  28. 2015Joint Object and Part Segmentation using Deep Learned Potentialscited by 23
  29. 2017Holistic, Instance-Level Human Parsingcited by 19
  30. 2019Fast Panoptic Segmentation Networkcited by 19
  31. 2018Cross-domain Human Parsing via Adversarial Feature and Label Adaptationcited by 11
  32. 2019Single Network Panoptic Segmentation for Street Scene Understandingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 11; 2023: 14; 2024: 16; 2025: 11; 2026: 2.

56 papers.

Sort:

By area:

  1. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  2. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  3. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  4. 2024GROUNDHOG: Grounding Large Language Models to Holistic Segmentationcited by 70
  5. 2023Hierarchical Open-vocabulary Universal Image Segmentationcited by 53
  6. 2023Going Denser with Open-Vocabulary Part Segmentationcited by 51
  7. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  8. 2023OV-PARTS: Towards Open-Vocabulary Part Segmentationcited by 31
  9. 2024SegLLM: Multi-round Reasoning Segmentationcited by 25
  10. 2023Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformerscited by 22
  11. 2024MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuningcited by 22
  12. 2023Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentationcited by 21
38 more
  1. 2024Subobject-level Image Tokenizationcited by 20
  2. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  3. 2021Panoptic Segmentation: A Reviewcited by 18
  4. 2023Deep Learning Technique for Human Parsing: A Survey and Outlookcited by 18
  5. 2022Uncertainty-aware Panoptic Segmentationcited by 17
  6. 2022Learning Hierarchical Image Segmentation For Recognition and By Recognitioncited by 16
  7. 2023Towards Open-World Segmentation of Partscited by 15
  8. 2024PartGLEE: A Foundation Model for Recognizing and Parsing Any Objectscited by 15
  9. 2024GraCo: Granularity-Controllable Interactive Segmentationcited by 13
  10. 2023Auxiliary Learning as an Asymmetric Bargaining Gamecited by 12
  11. 2025Reasoning Segmentation for Images and Videos: A Surveycited by 12
  12. 2022Visual Recognition by Requestcited by 10
  13. 2022FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsingcited by 9
  14. 2022Segmenting Known Objects and Unseen Unknowns without Prior Knowledgecited by 9
  15. 2025Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Predictioncited by 7
  16. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  17. 2022Multi-task Fusion for Efficient Panoptic-Part Segmentationcited by 6
  18. 2023AIMS: All-Inclusive Multi-Level Segmentationcited by 6
  19. 2024SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Imagescited by 5
  20. 2025Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularitiescited by 5
  21. 2024Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representationscited by 4
  22. 2024Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentationcited by 4
  23. 2024CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Modelscited by 4
  24. 2024Understanding Multi-Granularity for Open-Vocabulary Part Segmentationcited by 3
  25. 2025LLMs Can Compensate for Deficiencies in Visual Representationscited by 3
  26. 2022Parsing Objects at a Finer Granularity: A Surveycited by 2
  27. 2023Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesiscited by 2
  28. 2023JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentationcited by 2
  29. 2023EfficientPPS: Part-aware Panoptic Segmentation of Transparent Objects for Robotic Manipulationcited by 1
  30. 2024Inpainting the Gaps: A Novel Framework for Evaluating Explanation Methods in Vision Transformerscited by 1
  31. 2024Resolving Inconsistent Semantics in Multi-Dataset Image Segmentationcited by 1
  32. 2024Learning Representation for Multitask learning through Self Supervised Auxiliary learningcited by 1
  33. 2025Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learningcited by 1
  34. 2025LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentationcited by 1
  35. 2022Self-Supervised Road Layout Parsing with Graph Auto-Encodingcited by 0
  36. 2024Enabling Asymmetric Knowledge Transfer in Multi-Task Learning with Self-Auxiliariescited by 0
  37. 2024OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsingcited by 0
  38. 2025Dictionary-based Framework for Interpretable and Consistent Object Parsingcited by 0

50 most cited of 56 All 56 (JSON)