mlsanityData to 7 Oct 2026

Panoptic Feature Pyramid Networks

arXiv 1901.02446 ↗First posted 8 Jan 2019cs.CVcited by 644

Not on the map. Why?

Abstract (arXiv)

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation. In this work, we aim to unify these methods at the architectural level, designing a single network for both tasks. Our approach is to endow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone. Surprisingly, this simple baseline not only remains effective for instance segmentation, but also yields a lightweight, top-performing method for semantic segmentation. In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

Key facts. Cited by 644 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 102; 2022: 152; 2023: 176; 2024: 116; 2025: 70; 2026: 27.

644 papers.

Sort:

By area:

  1. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  2. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  5. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  6. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  7. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  10. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  11. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  12. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
38 more
  1. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  2. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  3. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  4. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  5. 2022Vision Transformer with Deformable Attentioncited by 293
  6. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  7. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  8. 2021Global Filter Networks for Image Classificationcited by 257
  9. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  10. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  11. 2021K-Net: Towards Unified Image Segmentationcited by 211
  12. 2022Visual Attention Networkcited by 210
  13. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  14. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
  15. 2023SegGPT: Segmenting Everything In Contextcited by 193
  16. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  17. 2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 170
  18. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 166
  19. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  20. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  21. 2023BiFormer: Vision Transformer with Bi-Level Routing Attentioncited by 150
  22. 2022Advancing Plain Vision Transformer Towards Remote Sensing Foundation Modelcited by 149
  23. 2022Audio-Visual Segmentationcited by 148
  24. 2021Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networkscited by 141
  25. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  26. 2022Open-Vocabulary Universal Image Segmentation with MaskCLIPcited by 131
  27. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  28. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  29. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  30. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  31. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  32. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  33. 2022Panoptic Scene Graph Generationcited by 114
  34. 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
  35. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  36. 2022An Empirical Study of Remote Sensing Pretrainingcited by 105
  37. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  38. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99

50 most cited of 644 All 644 (JSON)