mlsanityData to 7 Oct 2026

Multi-task Fusion for Efficient Panoptic-Part Segmentation

arXiv 2212.07671 ↗First posted 15 Dec 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows for mutually improved and consistent representation learning. To fuse the predictions of all three heads efficiently, we introduce a parameter-free joint fusion module that dynamically balances the logits and fuses them to create panoptic-part segmentation. Our method is evaluated on the Cityscapes Panoptic Parts (CPP) and Pascal Panoptic Parts (PPP) datasets. For CPP, the PartPQ of our proposed model with joint fusion surpasses the previous state-of-the-art by 1.6 and 4.7 percentage points for all areas and segments with parts, respectively. On PPP, our joint fusion outperforms a model using the previous top-down merging strategy by 3.3 percentage points in PartPQ and 10.5 percentage points in PartPQ for partitionable classes.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 44 of its 52 references that are in the map. First posted on arXiv 15 Dec 2022.

Builds on

44 of 52 references.

References · 44

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  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. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2018Panoptic Segmentationcited by 796
  9. 2019Panoptic Feature Pyramid Networkscited by 644
  10. 2020ResNeSt: Split-Attention Networkscited by 445
  11. 2019Panoptic-DeepLabcited by 362
  12. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
32 more
  1. 2019Self-Correction for Human Parsingcited by 179
  2. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  3. 2014Simultaneous Detection and Segmentationcited by 158
  4. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  5. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
  6. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 122
  7. 2019Seamless Scene Segmentationcited by 112
  8. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  9. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  10. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  11. 2019SSAP: Single-Shot Instance Segmentation With Affinity Pyramidcited by 85
  12. 2017In-Place Activated BatchNorm for Memory-Optimized Training of DNNscited by 81
  13. 2019Graphonomy: Universal Human Parsing via Graph Transfer Learningcited by 81
  14. 2015Learning to Segment Object Candidatescited by 79
  15. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  16. 2018Self-Supervised Model Adaptation for Multimodal Semantic Segmentationcited by 73
  17. 2018Devil in the Details: Towards Accurate Single and Multiple Human Parsingcited by 64
  18. 2019AdaptIS: Adaptive Instance Selection Networkcited by 64
  19. 2019DeeperLab: Single-Shot Image Parsercited by 63
  20. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  21. 2021Part-aware Panoptic Segmentationcited by 56
  22. 2018Parsing R-CNN for Instance-Level Human Analysiscited by 53
  23. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  24. 2018Weakly- and Semi-Supervised Panoptic Segmentationcited by 40
  25. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  26. 2020Unifying Training and Inference for Panoptic Segmentationcited by 37
  27. 2019Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregationcited by 34
  28. 2018Learning to Fuse Things and Stuffcited by 26
  29. 2020GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wildcited by 25
  30. 2017Holistic, Instance-Level Human Parsingcited by 19
  31. 2020Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understandingcited by 14
  32. 2018Cross-domain Human Parsing via Adversarial Feature and Label Adaptationcited by 11

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1; 2025: 1.

6 papers.

  1. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  2. 2023Hierarchical Open-vocabulary Universal Image Segmentationcited by 53
  3. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  4. 2024Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representationscited by 4
  5. 2023JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentationcited by 2
  6. 2025SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentationcited by 0