TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

By Jamie Shotton, John M. Winn, Carsten Rother, Antonio Criminisi. 2007

1,186 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

Microsoft COCO: Common Objects in Context (2014, background): “Datasets exist for both indoor [11] and outdoor [35], [14] scenes.”
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “Most of the successful semantic segmentation systems developed in the previous decade relied on hand-crafted features combined with flat classifiers, such as Boosting [24], [42], Random Forests [43], or Support Vector Machines [44].”
Delving into Egocentric Actions (2015, positive): “We apply textonBoost with CRF [32] for hand segmentation, and match the boundaries to different templates under four hand configurations as in [22].”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “6% result of TextonBoost (Shotton et al., 2009) to 29 .”
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; Krähenbühl & Koltun, 2011).”
Conditional Random Fields as Recurrent Neural Networks (2015, methodology): “Works on this topic include: TextonBoost [28], TextonForest [27], and Random Forest-based human body pose estimation for Kinect [26].”
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.”
ParseNet: Looking Wider to See Better (2015, methodology): “For tasks such as semantic segmentation, using context information [23, 25, 14] from the whole image can significantly help classifying local patches.”
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials (2011, methodology): “We report the standard measures of multi-class segmentation accuracy: “global” denotes the overall percentage of correctly classified image pixels and “average” is the unweighted average of per-category classification accuracy [19, 9].”
Feedforward semantic segmentation with zoom-out features (2014, methodology): “Many of the segmentations have moderate to high accuracy, capturing correct classes, in correct layout, and sometimes including level of detail that is usually missing from over-smoothed segmentations obtained by CRFs or generated by region proposals.”
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (2019, background): “It has been known that context information is crucial for pixel labeling tasks [26, 69, 37, 39, 16, 54, 14, 10].”
Knowledge Distillation for Incremental Learning in Semantic Segmentation (2019, methodology): “To evaluate the e ﬀ ectiveness and the robustness of the proposed methodologies we choose to employ two publicly available datasets for semantic segmentation: namely, the Pascal VOC2012 [49] and the MSRC-v2 [50] datasets.”
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].”
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding (2015, methodology): “Semantic pixel labelling was initially approached with TextonBoost [32], TextonForest [30] and Random Forest Based Classiﬁers [31].”
Higher Order Conditional Random Fields in Deep Neural Networks (2015, methodology): “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].”
What's the Point: Semantic Segmentation with Point Supervision (2015, methodology): “Strongly supervised methods require a training set of images with per-pixel annotations [32, 6, 22, 15, 9] (Fig.”
Laplacian Reconstruction and Refinement for Semantic Segmentation (2016, neutral): “This has allowed them to signiﬁcantly outperform previous approaches (e.g., [1,2,3]) that relied on hand-designed features and recognizers trained from scratch.”