Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection

By Jyri J. Kivinen, Christopher K. I. Williams, Nicolas Manfred Otto Heess. 2014

81 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

Holistically-Nested Edge Detection (2015, neutral): “….757 .696 1/240 Sketch Tokens [22] .727 .746 .780 1 SCG [29] .739 .758 .773 1/280 SE-Var [6] .746 .767 .803 2.5 OEF [12] .749 .772 .817 - DeepNets [19] .738 .759 .758 1 / 5 † N4-Fields [9] .753 .769 .784 1 / 6 † DeepEdge [2] .753 .772 .807 1/ 10 3 † CSCNN [17] .756 .775 .798 - DeepContour [32] .”
Fast Edge Detection Using Structured Forests (2014, background): “F”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, neutral): “We compare our method to some of the best-established methods of boundary detection [1, 23], as well as more recent, deep learning-based ones [6,28,41,48,49,90,107].”
Harmonic Networks: Deep Translation and Rotation Equivariance (2016, background): “We also compared with [14], who use a mean-andcovariance-RBM.”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, methodology): “These prior approaches share a bottom-up architecture where low-level features based on texture, saliency, or brightness are used as input to a classiﬁer, spectral method or other pipeline to perform contour predictions.”
Unsupervised Learning of Edges (2015, background): “Since the work of [10], which formulated edge detection as a binary classification problem, progressively more powerful learning paradigms have been employed, including multi-class classification [23], feature learning [30], regression [35], structured prediction [11], and deep learning [20, 5, 44].”
Pushing the Boundaries of Boundary Detection using Deep Learning (2015, background): “Method ODS OIS AP gPb-owt-ucm (Arbelaez et al., 2011) 0.726 0.757 0.696 SE-Var (Doll´ar & Zitnick, 2015) 0.746 0.767 0.803 DeepNets (Kivinen et al., 2014) 0.738 0.759 0.758 N4-Fields (Ganin & Lempitsky, 2014) 0.753 0.769 0.784 DeepEdge (Bertasius et al., 2015) 0.753 0.772 0.807 CSCNN (Hwang & Liu, 2”
N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms (2014, methodology): “In general, N 4 -ﬁelds perform similarly to the best previously published methods [20, 10, 26].”
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision (2015, methodology): “We also report the runtimes in Table 2 and note that our method runs faster than previous deep-learning based edge detection systems [27, 10, 16, 3].”
Oriented edge forests for boundary detection (2014, neutral): “77 DeepNet [13] .”
PixelNet: Towards a General Pixel-level Architecture (2016, unknown): “….640 .580 Felz-Hutt [23] .610 .640 .560 gPb-owt-ucm [2] .726 .757 .696 Sketch Tokens [44] .727 .746 .780 SCG [69] .739 .758 .773 PMI [37] .740 .770 .780 SE-Var [17] .746 .767 .803 OEF [30] .749 .772 .817 DeepNets [39] .738 .759 .758 CSCNN [34] .756 .775 .798 HED [71] .782 .804 .833 HED [71] not.”
Object Contour and Edge Detection with RefineContourNet (2019, methodology): “In recent years, edge detectors, such as DeepNet [14] and N-Fields [11] have begun to use operations from CNNs to reach a higherlevel detection.”
Deep Crisp Boundaries (2017, unknown): “756 DeepEdge [17] .”
DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection (2015, background): “However, obvious performance gap is still observed between contour detections given by the algorithms and human annotations.”
Dynamic Steerable Blocks in Deep Residual Networks (2017, background): “Note, that Kivinen and HED are non-pretrained re-implementations of [25, 39] reported in [37].”
Road crack detection using deep convolutional neural network (2016, background): “Index Terms— Deep learning, convolution neural networks, road crack detection, road survey”
Semantic Segmentation with Boundary Neural Fields (2015, methodology): “Whereas DeepNet and DeepContour optimize ordinary CNNs to a boundary based optimization criterion from scratch, DeepEdge and HFL employ pretrained models to compute boundaries.”
Privacy Protection for Natural Language Records: Neural Generative Models for Releasing Synthetic Twitter Data (2016, methodology): “In this paper we use only redaction of handles and hashtags, since it can be argued that these comprise the large majority of identifying entities in Twitter data.2”