Discriminatively Trained Sparse Code Gradients for Contour Detection

By Xiaofeng Ren, Liefeng Bo. 2012

289 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

What Makes for Effective Detection Proposals? (2015, background): “We aim to understand if detection proposals improve detection accuracy or if their use is strictly necessary for computational reasons.”
EDTER: Edge Detection with Transformer (2022, methodology): “We compare our model with traditional detectors including Canny [6], Felz-Hutt [18], gPb-owt-ucm [2], SCG [64], Sketch Tokens [34], PMI [25], SE [15], OEF [21] and MES [50], and deep-learning-based detectors including DeepEdge [3], CSCNN [24], DeepCon-tour [48], HFL [4], HED [65], Deep Boundary [29]”
Fast Edge Detection Using Structured Forests (2014, methodology): “The next three rows contain results for gPb-owt-ucm [1], Sketch Tokens [31], and SCG [41].”
Learning Rich Features from RGB-D Images for Object Detection and Segmentation (2014, methodology): “scribe how to extend multiscale combinatorial grouping (MCG) [1] to eectively utilize depth cues to obtain 2.5D region proposals. 2.1 Contour Detection RGB-D contour detection is a well-studied task [9,18,30,34]. Here we combine ideas from two leading approaches, [9] and our past work in [18]. In [1”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, methodology): “tend it with 20K 14 images of normal ground truth estimated from the raw images in the training scenes of [74]; since the method of [54] is not publicly available, we use as a surrogate the method of [86]. Competing methods, e.g. [2,25] are using alternative normal estimation methods for the extende”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, methodology): “ setting. Method ODS OIS AP Canny [7] 0.6 0.63 0.58 Mean Shift [8] 0.64 0.68 0.56 Ncuts [26] 0.64 0.68 0.45 Felz., Hutt. [10] 0.61 0.64 0.56 SCT [17] 0.71 0.72 0.74 gPb-owt-ucm [2] 0.73 0.76 0.73 SCG [23] 0.74 0.76 0.77 Sketch Tokens [16] 0.73 0.75 0.78 SE [9] 0.74 0.76 0.78 PMI [12] 0.74 0.77 0.78 ”
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].”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “490 SC [22] 0.”
Pushing the Boundaries of Boundary Detection using Deep Learning (2015, methodology): “…following the introduction of human-annotated datasets (Konishi et al., 2003; Martin et al., 2004), e.g. (Dollar et al., 2006; Arbelaez et al., 2011; Ren, 2008; Kokkinos, 2010a; Ren & Bo, 2012; Doll ´ ar & Zitnick, 2015), we use machine learning to optimize the performance of our boundary detector.”
N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms (2014, methodology): “Following the works [20, 25] we apply our scheme at different scales.”
High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object Features and Its Applications to High-Level Vision (2015, methodology): “d about the procedure for boundary detection evaluation on the BSDS500 dataset. One issue with the BSDS500 dataset involves the so called “orphan” boundaries: the boundConsensus GT ODS OIS AP FPS SCG [23] 0.6 0.64 0.56 1/280 DeepNet [16] 0.61 0.64 0.61 1=5z PMI [14] 0.61 0.68 0.56 1/900 DeepEdge [3]”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, background): “Ren and Bo [17] use sparse coding and oriented gradients to learn dictionaries of contour patches.”
Oriented edge forests for boundary detection (2014, neutral): “Recently, focus has turned to methods that learn appropriate feature representations from training data rather than relying on carefully hand-designed texture and brightness contrast measures.”
PixelNet: Towards a General Pixel-level Architecture (2016, unknown): “Human [2] .800 .800 - Canny .600 .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…”
Histograms of Sparse Codes for Object Detection (2013, background): “as is sometimes done in recognition settings [26].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Reasoning from Blocks to Stability (background): “…that integrating depth with color information improves the performances of many vision tasks, such as segmentation (in [7]), contour detection (in [24]), object recognition (in [25], [26], and [27]), scene labeling (in [28], [29], [30] and [31]), and activity detection (in [32], [33] and [34]).”
Bi-Directional Cascade Network for Perceptual Edge Detection (2019, methodology): “COB [32], HED [49], HFL [3], DeepEdge [2] and Deep-Contour [42], and traditional edge detection methods, including SCG [40], PMI [20] and OEF [17].”
Semantic Image Segmentation with Contextual Hierarchical Models (2015, methodology): “Moreover, we will demonstrate that generalization performance of CHM across different datasets is better compared to [11], [12].”
Visual Boundary Prediction: A Deep Neural Prediction Network and Quality Dissection (2014, background): “, 2011], SCG [Ren and Bo, 2012], Sketch Tokens [Lim et al.”