mlsanityData to 7 Oct 2026

Exemplar-Based Open-Set Panoptic Segmentation Network

arXiv 2105.08336 ↗First posted 18 May 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

We extend panoptic segmentation to the open-world and introduce an open-set panoptic segmentation (OPS) task. This task requires performing panoptic segmentation for not only known classes but also unknown ones that have not been acknowledged during training. We investigate the practical challenges of the task and construct a benchmark on top of an existing dataset, COCO. In addition, we propose a novel exemplar-based open-set panoptic segmentation network (EOPSN) inspired by exemplar theory. Our approach identifies a new class based on exemplars, which are identified by clustering and employed as pseudo-ground-truths. The size of each class increases by mining new exemplars based on the similarities to the existing ones associated with the class. We evaluate EOPSN on the proposed benchmark and demonstrate the effectiveness of our proposals. The primary goal of our work is to draw the attention of the community to the recognition in the open-world scenarios. The implementation of our algorithm is available on the project webpage: https://cv.snu.ac.kr/research/EOPSN.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 41 of its 58 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

41 of 58 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2014Going Deeper with Convolutionscited by 4,231
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  12. 2017Prototypical Networks for Few-shot Learningcited by 3,001
29 more
  1. 2015Fast R-CNNcited by 2,930
  2. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  4. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  5. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2018Panoptic Segmentationcited by 796
  8. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  9. 2019Panoptic Feature Pyramid Networkscited by 644
  10. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  11. 2015Towards Open Set Deep Networkscited by 533
  12. 2019YOLACT: Real-time Instance Segmentationcited by 441
  13. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  14. 2019Panoptic-DeepLabcited by 362
  15. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  16. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  17. 2018Bilinear Attention Networkscited by 277
  18. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
  19. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  20. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  21. 2019Seamless Scene Segmentationcited by 112
  22. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  23. 2018Attention-guided Unified Network for Panoptic Segmentationcited by 71
  24. 2019DeeperLab: Single-Shot Image Parsercited by 63
  25. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  26. 2018Weakly- and Semi-Supervised Panoptic Segmentationcited by 40
  27. 2019Learning Instance Occlusion for Panoptic Segmentationcited by 30
  28. 2018Bayesian Semantic Instance Segmentation in Open Set Worldcited by 14
  29. 2019IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of Thingscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 10; 2024: 6; 2025: 5; 2026: 4.

37 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  2. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  3. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  4. 2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
  5. 2022Expanding Low-Density Latent Regions for Open-Set Object Detectioncited by 38
  6. 2023Picture that Sketch: Photorealistic Image Generation from Abstract Sketchescited by 34
  7. 2023Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentationcited by 28
  8. 2022OpenTAL: Towards Open Set Temporal Action Localizationcited by 23
  9. 2021Panoptic Segmentation: A Reviewcited by 18
  10. 2023Mask2Anomaly: Mask Transformer for Universal Open-set Segmentationcited by 18
  11. 2023SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learningcited by 17
  12. 2023UGainS: Uncertainty Guided Anomaly Instance Segmentationcited by 15
25 more
  1. 2022CoGS: Controllable Generation and Search from Sketch and Stylecited by 14
  2. 2023Panoptic Out-of-Distribution Segmentationcited by 13
  3. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  4. 2022Learning to Discover and Detect Objectscited by 11
  5. 2025Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Drivingcited by 10
  6. 2022Segmenting Known Objects and Unseen Unknowns without Prior Knowledgecited by 9
  7. 2022Dual Decision Improves Open-Set Panoptic Segmentationcited by 8
  8. 2024OoDIS: Anomaly Instance Segmentation and Detection Benchmarkcited by 8
  9. 2022GOSS: Towards Generalized Open-set Semantic Segmentationcited by 7
  10. 2024Lidar Panoptic Segmentation in an Open Worldcited by 7
  11. 2025Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentationcited by 7
  12. 2026Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Languagecited by 6
  13. 2025Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learningcited by 5
  14. 2024PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentationcited by 4
  15. 2021Reconstruction guided Meta-learning for Few Shot Open Set Recognitioncited by 3
  16. 2023ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Datacited by 3
  17. 2024Open-World Panoptic Segmentationcited by 2
  18. 2025SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketchescited by 1
  19. 2021KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentationcited by 0
  20. 2022Panoptic Segmentation using Synthetic and Real Datacited by 0
  21. 2024A Bottom-Up Approach to Class-Agnostic Image Segmentationcited by 0
  22. 2025A Machine Learning Perspective on Automated Driving Corner Casescited by 0
  23. 2026Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentationcited by 0
  24. 2026FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentationcited by 0
  25. 2026Learning from Multimodal Pseudo-Labels for Robust Open-Vocabulary Instance and Panoptic Segmentationcited by 0