Contour Detection and Hierarchical Image Segmentation

By Pablo Arbeláez, Michael Maire, Charless C. Fowlkes, Jitendra Malik. 2011

5,808 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, methodology): “The Berkeley Segmentation Data Set (BSDS500) [37] has been used extensively to evaluate both segmentation and edge detection algorithms.”
What Makes for Effective Detection Proposals? (2015, background): “Sliding window classifiers scale linearly with the number of windows tested, and while single-scale detection requires classifying around 104 – 105 windows per image, the number of windows grows by an order of magnitude for multi-scale detection.”
Unsupervised Domain Adaptation by Backpropagation (2014, methodology): “In order to obtain the target domain (MNIST-M) we blend digits from the original set over patches randomly extracted from color photos from BSDS500 (Arbelaez et al., 2011).”
EDTER: Edge Detection with Transformer (2022, methodology): “We compare our model with traditional detectors including Canny [6], Felz-Hutt [18], gPb-owtucm [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], DeepContour [48], HFL [4], HED [65], Deep Boundary [29], ”
Extreme Clicking for Efficient Object Annotation (2017, methodology): “For these experiments we use structured edge forests [15] to predict object boundaries, which is trained on BSD500 [2].”
Holistically-Nested Edge Detection (2015, methodology): “…perform the majority of the experiments on the Berkeley Segmentation Dataset and Bench-6 [8] .610 .640 .560 10 BEL [5] .660 ∗ - - 1/10 gPb-owt-ucm [1] .726 .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 -…”
Fast Edge Detection Using Structured Forests (2014, background): “Second, by default our model can only output examples observed during training (although this can be ameliorated with custom ensemble models).”
Conditional Random Fields as Recurrent Neural Networks (2015, neutral): “BerkeleyRC [3] n/a 39.”
Domain-Adversarial Training of Neural Networks (2015, methodology): “In order to obtain the target domain ( MNIST-M ) we blend digits from the original set over patches randomly extracted from color photos from BSDS500 (Arbelaez et al., 2011).”
Learning Rich Features from RGB-D Images for Object Detection and Segmentation (2014, methodology): “In [18], we used gPb-ucm [2] and proposed local geometric gradients dubbed NG−, NG+, and DG to capture convex, concave normal gradients and depth gradients.”
Semantic Image Segmentation via Deep Parsing Network (2015, background): “Existing works such as [31, 29, 9, 34, 11, 2, 8, 25, 22] can be generally categorized into two groups based on their definitions of the unary and pairwise terms of MRF.”
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].”
Learning visual groups from co-occurrences in space and time (2015, methodology): “Visual grouping is also a central problem in computer vision, showing up in the tasks of edge/contour detection Canny (1986); Arbelaez et al. (2011); Isola et al. (2014) , (semantic) segmentation Shi & Malik (2000); Malisiewicz & Efros (2007), and object proposals Alexe et al. (2012); Zitnick &…”
Synthetic Data for Text Localisation in Natural Images (2016, methodology): “Regions are obtained by thresholding the gPb-UCM contour hierarchies [2] at 0.”
On the Binding Problem in Artificial Neural Networks (2020, background): “Image segmentation is concerned with segmenting the pixels (or edges Arbeláez et al., 2011) belonging to an image into groups (e.g. objects) and therefore provides a good starting point for segregation.”