… We propose a method for estimating uncertainties for automatic detection of channel bodies
in seismic volumes using a Bayesian encoder-decoder CNN with a dropout layer and noise …

… encoder–decoder architecture) to segment objects of different sizes within the same image
[3]. The encoder–decoder architecture … ), showing that the model uncertain of its prediction for …

… Bayesian deep learning method, based on Monte Carlo Dropout, is proposed to tackle semantic
segmentation of aerial and satellite images. Bayesian deep learning … model uncertainty) …

… neural networks for image semantic segmentation, which takes the encoderdecoder
architecture to recover the spatial information and utilizes multi-scale features by using atrous …

… CNN-based architectures for image segmentation comprise of an encoder-decoder network,
which … Based on this encoder-decoder structure, the input is thereby refined to obtain the …

… methods used for measuring and evaluating model uncertainty. Bayesian neural networks
… What uncertainties do we need in bayesian deep learning for computer vision? In Advances …

… model uncertainty or confidence. This paper introduces a new Bayesian DL framework for
uncertainty … image Segmentation with Uncertainty Propagation in EncoderdecodeR Networks. …

… Our model uses a similar encoder decoder architecture as that used in VAEs with the input
to the encoder coming from a pre trained image segmentation architecture. We tried different …

… [20] presented Bayesian SegNet, the first probabilistic semantic segmentation approach
using deep learning. The proposed method is an extension of SegNet, an encoder–decoder …

… Bayesian SegNet for uncertainty evaluation. This paper first simplifies the network structure
of Bayesian SegNet by … the Bayesian SegNet and applying the pyramid pooling model to …