Corpus ID: 54208798

Evaluating Bayesian Deep Learning Methods for Semantic Segmentation

@article{Mukhoti2018EvaluatingBD,
  title={Evaluating Bayesian Deep Learning Methods for Semantic Segmentation},
  author={Jishnu Mukhoti and Yarin Gal},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.12709}
}
  • Jishnu Mukhoti, Yarin Gal
  • Published 2018
  • Computer Science
  • ArXiv
  • Deep learning has been revolutionary for computer vision and semantic segmentation in particular, with Bayesian Deep Learning (BDL) used to obtain uncertainty maps from deep models when predicting semantic classes. [...] Key Method We modify DeepLab-v3+, one of the state-of-the-art deep neural networks, and create its Bayesian counterpart using MC dropout and Concrete dropout as inference techniques. We then compare and test these two inference techniques on the well-known Cityscapes dataset using our suggested…Expand Abstract
    35 Citations
    Probabilistic Deep Learning for Instance Segmentation
    Fishyscapes: A Benchmark for Safe Semantic Segmentation in Autonomous Driving
    • 5
    • Highly Influenced
    • PDF
    Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision
    • 23
    • Highly Influenced
    • PDF
    Bayesian Uncertainty Quantification with Synthetic Data
    • 4
    • PDF
    Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
    Scalable Uncertainty for Computer Vision With Functional Variational Inference
    • 1
    • PDF
    Bayesian Deep Learning and Uncertainty in Computer Vision
    • 1
    Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference
    • 6
    • PDF

    References

    SHOWING 1-10 OF 70 REFERENCES
    Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
    • 2,511
    • Highly Influential
    • PDF
    Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
    • 661
    • PDF
    RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
    • 1,108
    • PDF
    What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
    • 1,138
    • PDF
    Semantic Image Segmentation via Deep Parsing Network
    • 471
    • PDF
    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    • 5,600
    • PDF
    Attention to Scale: Scale-Aware Semantic Image Segmentation
    • 672
    • PDF
    Recurrent Convolutional Neural Networks for Scene Labeling
    • 579
    • PDF