mlsanityData to 14 Oct 2026

Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation

arXiv 2207.11860 ↗First posted 25 Jul 2022cs.CV cs.RO eess.IVcited by 46

Not on the map. Why?

Abstract (arXiv)

In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360deg imagery. To tackle these problems, first, we propose the upgraded Transformer for Panoramic Semantic Segmentation, i.e., Trans4PASS+, equipped with Deformable Patch Embedding (DPE) and Deformable MLP (DMLPv2) modules for handling object deformations and image distortions whenever (before or after adaptation) and wherever (shallow or deep levels). Second, we enhance the Mutual Prototypical Adaptation (MPA) strategy via pseudo-label rectification for unsupervised domain adaptive panoramic segmentation. Third, aside from Pinhole-to-Panoramic (Pin2Pan) adaptation, we create a new dataset (SynPASS) with 9,080 panoramic images, facilitating Synthetic-to-Real (Syn2Real) adaptation scheme in 360deg imagery. Extensive experiments are conducted, which cover indoor and outdoor scenarios, and each of them is investigated with Pin2Pan and Syn2Real regimens. Trans4PASS+ achieves state-of-the-art performances on four domain adaptive panoramic semantic segmentation benchmarks. Code is available at https://github.com/jamycheung/Trans4PASS.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Builds on 120 of its 151 references that are in the map. First posted on arXiv 25 Jul 2022.

Builds on

120 of 151 references.

References · 120

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2017Squeeze-and-Excitation Networkscited by 4,789
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  2. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  3. 2016Pyramid Scene Parsing Networkcited by 2,479
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  8. 2017Deformable Convolutional Networkscited by 1,488
  9. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  10. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  13. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  14. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  15. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  16. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  17. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  18. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  19. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  20. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  21. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  22. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  23. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  24. 2019Panoptic Feature Pyramid Networkscited by 645
  25. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  26. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  27. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  28. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  29. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  30. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  31. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  32. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  33. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  34. 2020ResNeSt: Split-Attention Networkscited by 445
  35. 2019Confidence Regularized Self-Trainingcited by 419
  36. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  37. 2021AdaViT: Adaptive Tokens for Efficient Vision Transformercited by 362
  38. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308

50 most cited of 120 All 120 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 13; 2025: 12; 2026: 14.

46 papers.

Sort:

By area:

  1. 2023Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentationcited by 38
  2. 2024Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentationcited by 34
  3. 2024GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentationcited by 28
  4. 2024360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypescited by 28
  5. 2025OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentationcited by 28
  6. 2023SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentationcited by 26
  7. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
  8. 2025Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?cited by 23
  9. 2023360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye Viewcited by 18
  10. 2023Single Frame Semantic Segmentation Using Multi-Modal Spherical Imagescited by 18
  11. 2024Open Panoramic Segmentationcited by 17
  12. 2025Omnidirectional Multi-Object Trackingcited by 13
34 more
  1. 2023SAM4UDASS: When SAM Meets Unsupervised Domain Adaptive Semantic Segmentation in Intelligent Vehiclescited by 12
  2. 2024Vision transformers in domain adaptation and domain generalization: a study of robustnesscited by 11
  3. 2024GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentationcited by 11
  4. 2023DarSwin: Distortion Aware Radial Swin Transformercited by 10
  5. 2024360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videoscited by 8
  6. 2024Multi-source Domain Adaptation for Panoramic Semantic Segmentationcited by 8
  7. 2025QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robotscited by 8
  8. 2024Occlusion-Aware Seamless Segmentationcited by 7
  9. 2024Deformable Mamba for Wide Field of View Segmentationcited by 7
  10. 2023FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentationcited by 6
  11. 2026MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priorscited by 5
  12. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 5
  13. 2025Rethinking Generalizable Infrared Small Target Detection: A Real-scene Benchmark and Cross-view Representation Learningcited by 4
  14. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 4
  15. 2025OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedbackcited by 4
  16. 2026PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusioncited by 4
  17. 2026More than the Sum: Panorama-Language Models for Adverse Omni-Scenescited by 4
  18. 2024Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaborationcited by 3
  19. 2025E-SAM: Training-Free Segment Every Entity Modelcited by 3
  20. 2025Panoramic Out-of-Distribution Segmentationcited by 2
  21. 2026O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Roboticscited by 2
  22. 2024DarSwin-Unet: Distortion Aware Encoder-Decoder Architecturecited by 1
  23. 2025360-Degree Full-view Image Segmentation by Spherical Convolution compatible with Large-scale Planar Pre-trained Modelscited by 1
  24. 2025Neural Rendering for Sensor Adaptation in 3D Object Detectioncited by 1
  25. 2026JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramascited by 1
  26. 2026Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentationcited by 1
  27. 2026Denoise and Align: Towards Source-Free UDA for Robust Panoramic Semantic Segmentationcited by 1
  28. 2026Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modelingcited by 1
  29. 2026AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentationcited by 1
  30. 2026PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipelinecited by 1
  31. 2024An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentationcited by 0
  32. 2026SAP: Segment Any 4K Panoramacited by 0
  33. 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detectioncited by 0
  34. 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Cameracited by 0