Robust Higher Order Potentials for Enforcing Label Consistency

By Pushmeet Kohli, Lubor Ladicky, Philip H. S. Torr. 2008

1,040 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Model Architectures

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

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Jitendra Malik
4. Dacheng Tao
5. Xiaogang Wang
6. Alan L. Yuille
7. Trevor Darrell
8. Andrew Zisserman

In Model Architectures

1. Alan L. Yuille
2. Philip H. S. Torr
3. Liang-Chieh Chen
4. Kaiming He
5. Vladlen Koltun
6. Chunhua Shen
7. Quoc V. Le
8. Raquel Urtasun

Citations in the corpus

• COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Boundary complexity is defined as the ratio of pixels that have any neighboring pixel with a different semantic label (as in the boundary evaluation in [8, 32, 33]).”
• 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): “In this subsection, we evaluate the segmentation accuracy with the trimap experiment [36, 37, 9] to quantify the accuracy of the proposed decoder module near object boundaries.”
• Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “It has been shown that global features or contextual interactions [28, 65, 36, 40, 22, 77] are beneficial in correctly classifying pixels for semantic segmentation.”
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials (2011, methodology): “(c) Classification produced by the Robust P CRF [9].”
• 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].”
• Higher Order Conditional Random Fields in Deep Neural Networks (2015, methodology): “However, potentials defined on higher order cliques have been shown to be useful in previous works such as [21, 48].”
• PointRend: Image Segmentation As Rendering (2019, methodology): “The common approach to evaluate segmentation accuracy around boundaries is to calculate IoU for a “trimap”, a narrow band surrounding segment boundaries [27, 38, 4, 26].”
• Learning message-passing inference machines for structured prediction (2011, methodology): “Another is the high-order [8], associative M(3)N [20] model from [14]; we use their implementation5.”
• Recurrent Pixel Embedding for Instance Grouping (2017, methodology): “This partition into figure/boundary/background is sometimes referred to as a tri-map in the matting literature and has been previously utilized in analyzing semantic segmentation performance [43, 10, 28].”
• Laplacian Reconstruction and Refinement for Semantic Segmentation (2016, methodology): “This partitioning into figure/boundary/background is sometimes referred to as a tri-map in the matting literature and has been previously utilized in analyzing semantic segmentation performance [12,30].”