mlsanityData to 14 Oct 2026

Transmission-Guided Bayesian Generative Model for Smoke Segmentation

arXiv 2303.00900 ↗First posted 2 Mar 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Smoke segmentation is essential to precisely localize wildfire so that it can be extinguished in an early phase. Although deep neural networks have achieved promising results on image segmentation tasks, they are prone to be overconfident for smoke segmentation due to its non-rigid shape and transparent appearance. This is caused by both knowledge level uncertainty due to limited training data for accurate smoke segmentation and labeling level uncertainty representing the difficulty in labeling ground-truth. To effectively model the two types of uncertainty, we introduce a Bayesian generative model to simultaneously estimate the posterior distribution of model parameters and its predictions. Further, smoke images suffer from low contrast and ambiguity, inspired by physics-based image dehazing methods, we design a transmission-guided local coherence loss to guide the network to learn pair-wise relationships based on pixel distance and the transmission feature. To promote the development of this field, we also contribute a high-quality smoke segmentation dataset, SMOKE5K, consisting of 1,400 real and 4,000 synthetic images with pixel-wise annotation. Experimental results on benchmark testing datasets illustrate that our model achieves both accurate predictions and reliable uncertainty maps representing model ignorance about its prediction. Our code and dataset are publicly available at: https://github.com/redlessme/Transmission-BVM.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 64 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

39 of 64 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  12. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
27 more
  1. 2015Weight Uncertainty in Neural Networkscited by 554
  2. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  3. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 331
  4. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
  5. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  6. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  7. 2019F3Net: Fusion, Feedback and Focus for Salient Object Detectioncited by 176
  8. 2020Data Uncertainty Learning in Face Recognitioncited by 134
  9. 2021Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embeddingcited by 134
  10. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  11. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  12. 2020Segmenting Transparent Objects in the Wildcited by 98
  13. 2020UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoderscited by 98
  14. 2016Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypothesescited by 97
  15. 2018Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Featurescited by 81
  16. 2021Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Predictioncited by 57
  17. 2020Uncertainty Inspired RGB-D Saliency Detectioncited by 56
  18. 2021RGB-D Saliency Detection via Cascaded Mutual Information Minimizationcited by 50
  19. 2021Enhanced Boundary Learning for Glass-like Object Segmentationcited by 48
  20. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  21. 2019Supervised Uncertainty Quantification for Segmentation with Multiple Annotationscited by 42
  22. 2015Early Stopping is Nonparametric Variational Inferencecited by 23
  23. 2018Deep Smoke Segmentationcited by 12
  24. 2017Label Refinement Network for Coarse-to-Fine Semantic Segmentationcited by 11
  25. 2017A Deep Convolutional Neural Network for Background Subtractioncited by 5
  26. 2018Video Smoke Detection Based on Deep Saliency Networkcited by 3
  27. 2020Uncertainty-Aware Deep Calibrated Salient Object Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 2; 2026: 2.

6 papers.

  1. 2025SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detectioncited by 5
  2. 2023Model Calibration in Dense Classification with Adaptive Label Perturbationcited by 3
  3. 2023FoSp: Focus and Separation Network for Early Smoke Segmentationcited by 2
  4. 2025Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularizationcited by 1
  5. 2026Hyperspectral Smoke Segmentation via Mixture of Prototypescited by 0
  6. 2026AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation datasetcited by 0