mlsanityData to 14 Oct 2026

Hyperbolic Uncertainty Aware Semantic Segmentation

arXiv 2203.08881 ↗First posted 16 Mar 2022cs.CV cs.ROcited by 17

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, many works have shown that most misclassified pixels are commonly near object boundaries with high uncertainties. However, existing SS loss functions are not tailored to handle these uncertain pixels during training, as these pixels are usually treated equally as confidently classified pixels and cannot be embedded with arbitrary low distortion in Euclidean space, thereby degenerating the performance of SS. To overcome this problem, this paper designs a "Hyperbolic Uncertainty Loss" (HyperUL), which dynamically highlights the misclassified and high-uncertainty pixels in Hyperbolic space during training via the hyperbolic distances. The proposed HyperUL is model agnostic and can be easily applied to various neural architectures. After employing HyperUL to three recent SS models, the experimental results on Cityscapes and UAVid datasets reveal that the segmentation performance of existing SS models can be consistently improved.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

36 of 53 references.

References · 36

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2017On Calibration of Modern Neural Networkscited by 4,960
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  10. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  11. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  12. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
24 more
  1. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  2. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  3. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  4. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  5. 2018Hyperbolic Neural Networkscited by 402
  6. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  7. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  8. 2019Hyperbolic Image Embeddingscited by 221
  9. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  10. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  11. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  12. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  13. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  14. 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
  15. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  16. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  17. 2022Hyperbolic Image Segmentationcited by 102
  18. 2019DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationcited by 100
  19. 2018Direct Uncertainty Prediction for Medical Second Opinionscited by 61
  20. 2017Real-time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNscited by 55
  21. 2019Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classificationcited by 36
  22. 2021Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistancecited by 22
  23. 2021Semantic Segmentation with Labeling Uncertainty and Class Imbalancecited by 12
  24. 2022Self-Distribution Distillation: Efficient Uncertainty Estimationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 7; 2026: 3.

17 papers.

Sort:

By area:

  1. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 73
  2. 2023Poincar'e ResNetcited by 25
  3. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  4. 2025HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learningcited by 17
  5. 2023U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentationcited by 11
  6. 2024Hyperbolic Learning with Multimodal Large Language Modelscited by 10
  7. 2024A Fashion Item Recommendation Model in Hyperbolic Spacecited by 7
  8. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  9. 2025Continual Hyperbolic Learning of Instances and Classescited by 5
  10. 2025HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priorscited by 2
  11. 2025HySurvPred: Multimodal Hyperbolic Embedding with Angle-Aware Hierarchical Contrastive Learning and Uncertainty Constraints for Survival Predictioncited by 2
  12. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
5 more
  1. 2025Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detectioncited by 1
  2. 2025A Set-to-Set Distance Measure in Hyperbolic Spacecited by 0
  3. 2026Learning Action Hierarchies via Hybrid Geometric Diffusioncited by 0
  4. 2026Lorentz Framework for Semantic Segmentationcited by 0
  5. 2026Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagerycited by 0