Gaussian Conditional Random Field Network for Semantic Segmentation

By Raviteja Vemulapalli, Oncel Tuzel, Ming-Yu Liu, Ramalingam Chellappa. 2016

151 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Ocean Engineering

In Probabilistic & Bayesian Methods

Citations in the corpus

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, neutral): “7 MERL_DEEP_GCRF [88] 73.”
Pyramid Scene Parsing Network (2016, neutral): “5 GCRF [36] 85.”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, background): “, image pyramid) [18, 16, 58, 44, 11, 9] or those that adopt probabilistic graphical models (such as DenseCRF [37] with efficient inference algorithm [2]) [8, 4, 82, 44, 48, 55, 63, 34, 72, 6, 7, 9].”
Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “Recently, [37] proposes to learn a general and sparse high-dimensional convolution (bilateral convolution), and [73, 7] combine Gaussian Conditional Random Fields and DCNNs for semantic segmentation.”
Context Encoding for Semantic Segmentation (2018, neutral): “5 GCRF [47] 85.”
Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs (2016, methodology): “For instance the techniques of [1,2,3,10] perform mean-field inference for a fixed number of 10 iterations.”
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing (2020, methodology): “Early techniques for modeling contextual relationships for scene parsing involve the conditional random ﬁelds (CRFs) [25, 49, 1, 67].”
Asymmetric Non-Local Neural Networks for Semantic Segmentation (2019, methodology): “[31] integrated Gaussian Conditional Random Fields into CNNs and achieved relatively good results.”
Fast End-to-End Trainable Guided Filter (2018, background): “In computer vision tasks, a fully-connected conditional random field is usually applied [8, 44, 38], which relies on bilateral filter and runs slowly.”
Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology (2019, unknown): “In particular, graphical model [8][22][48][39], spatial pyramid pooling [8][9][47], dilated convolution [46] and multi-scale inputs (i.”
Survey on semantic segmentation using deep learning techniques (2019, methodology): “Figure 14 shows CRF as RNN. Vemulapalli et al. [163] proposed a model named Gaussian Mean Field (GMF) network that models unary potentials, pairwise potentials and Gaussian CRF inference for the task of semantic segmentation.”
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings (2017, background): “Regarding (a), [2, 26, 27, 28, 33, 34, 40] showed that structured prediction can be unfolded in time and thus be trained end-to-end with CNNs for both sparselyconnected [33] and fully-connected [26, 28, 34, 40] graphical structures.”
SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting (2018, unknown): “In [36, 44], they propose to incorporate an extra Conditional Random Fields module to encode long-range context.”
Weakly Supervised Semantic Segmentation Using Web-Crawled Videos (2017, background): “Semantic segmentation has recently achieved prominent progress thanks to Deep Convolutional Neural Networks (DCNNs) [3, 21, 24, 32, 37, 41].”