mlsanityData to 14 Oct 2026

U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation

arXiv 2307.09947 ↗First posted 19 Jul 2023cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their deployment in safety-critical applications like autonomous driving. In this regard, quantifying the uncertainty inherent to a model's prediction is a promising endeavour to address these shortcomings. In this work, we present a novel Uncertainty-aware Cross-Entropy loss (U-CE) that incorporates dynamic predictive uncertainties into the training process by pixel-wise weighting of the well-known cross-entropy loss (CE). Through extensive experimentation, we demonstrate the superiority of U-CE over regular CE training on two benchmark datasets, Cityscapes and ACDC, using two common backbone architectures, ResNet-18 and ResNet-101. With U-CE, we manage to train models that not only improve their segmentation performance but also provide meaningful uncertainties after training. Consequently, we contribute to the development of more robust and reliable segmentation models, ultimately advancing the state-of-the-art in safety-critical applications and beyond.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

30 of 50 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  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. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  8. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  9. 2017Mixed Precision Trainingcited by 1,156
  10. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  11. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  12. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
18 more
  1. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  2. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  3. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  4. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  5. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  6. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  7. 2020A survey of loss functions for semantic segmentationcited by 217
  8. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  9. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  10. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  11. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  12. 2018Lightweight Probabilistic Deep Networkscited by 77
  13. 2022Hyperbolic Uncertainty Aware Semantic Segmentationcited by 17
  14. 2023DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentationcited by 15
  15. 2021Semantic Segmentation with Labeling Uncertainty and Class Imbalancecited by 12
  16. 2022Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigationcited by 11
  17. 2023Compensation Learning in Semantic Segmentationcited by 5
  18. 2023Segmentation of Industrial Burner Flames: A Comparative Study from Traditional Image Processing to Machine and Deep Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

11 papers.

  1. 2024Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimationcited by 6
  2. 2025Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustnesscited by 3
  3. 2024A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimationcited by 2
  4. 2025A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimationcited by 2
  5. 2024Instance-wise Uncertainty for Class Imbalance in Semantic Segmentationcited by 0
  6. 2025NSegment : Label-specific Deformations for Remote Sensing Image Segmentationcited by 0
  7. 2025Distributional Uncertainty for Out-of-Distribution Detectioncited by 0
  8. 2025Unlocking Robust Semantic Segmentation Performance via Label-only Elastic Deformations against Implicit Label Noisecited by 0
  9. 2026Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learningcited by 0
  10. 2026An Uncertainty-Aware Loss Function Incorporating Fuzzy Logic: Application to MRI Brain Image Segmentationcited by 0
  11. 2026U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable explorationcited by 0