Multiscale conditional random fields for image labeling

By Xuming He, Richard S. Zemel, M. A. Carreira-Perpiñán. 2004

1,058 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, background): “Even thoughworks of increased sophistication have been proposed to model the hierarchical dependency [26], [27], [28] and/or high-order dependencies”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “Our loss function is the sum of cross-entropy terms for each spatial position in the CNN output map (subsampled by 8 compared to the original image).”
Multi-Scale Context Aggregation by Dilated Convolutions (2015, background): “A prominent example is semantic segmentation, which calls for classifying each pixel into one of a given set of categories (He et al., 2004; Shotton et al., 2009; Kohli et al., 2009; Kr ¨ ahenb ¨ uhl & Koltun, 2011).”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, methodology): “There are several model variants proposed to exploit the contextual information for segmentation [28, 65, 36, 39, 22, 79, 51, 14], including those that employ multi-scale inputs (i.”
Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “It has been shown that global features or contextual interactions [29, 67, 38, 42, 23, 80] are beneﬁcial in correctly classifying pixels for semantic segmentation.”
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials (2011, methodology): “In order to improve segmentation and labeling accuracy, researchers have expanded the basic CRF framework to incorporate hierarchical connectivity and higher-order potentials defined on image regions [8, 12, 9, 13].”
How to Represent Part-Whole Hierarchies in a Neural Network (2021, background): “2. it replaces a single ﬁeld of spins with ﬁelds at multiple levels, and allows adjacent level embeddings of the same location to interact [He et al., 2004, Saremi and Sejnowski, 2013].”
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2017, methodology): “Existing approaches to model uncertainty in such settings in computer vision include particle filtering and conditional random fields [3, 4].”
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (2018, background): “A critical element of building such systems is supplying global features and context information to perform pixel-level classification [35, 78, 41, 45, 31, 92, 60, 19, 63].”
Playing for Data: Ground Truth from Computer Games (2016, background): “First, we tackle the problem of semantic segmentation, which involves both recognition and perceptual grouping [17, 23, 28, 44].”
Higher Order Conditional Random Fields in Deep Neural Networks (2015, background): “The individual predictions made by these classifiers were often noisy as they lacked global context, and were thus post-processed with a CRF, making use of prior knowledge such as the fact that nearby pixels, as well as pixels of similar appearance, are likely to share the same class label [14, 15].”
R-CNN minus R (2015, neutral): “Our ﬁndings are summarised in Section 5.”
Bottom-up Instance Segmentation using Deep Higher-Order CRFs (2016, methodology): “Semantic Segmentation: This task was traditionally performed by extracting dense features from an image and classifying them on a per-pixel or per-region basis [16, 31].”
DeeperLab: Single-Shot Image Parser (2019, background): “Region-based metrics measure the proportion of correctly labelled pixels, including overall pixel accuracy [23, 24], mean class accuracy [24], and mean IOU (intersection-”
Figure/Ground Assignment in Natural Images (2006, methodology): “It has been previously applied to image labeling [20, 21], as well as contour completion [16].”
Putting Objects in Perspective (2006, background): “lationships between objects and other objects [15, 18], regions [10, 16, 28] or scene categories [18, 24], all within the 2D image.”